LUKE
Overview
The LUKE model was proposed in LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention by Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda and Yuji Matsumoto. It is based on RoBERTa and adds entity embeddings as well as an entity-aware self-attention mechanism, which helps improve performance on various downstream tasks involving reasoning about entities such as named entity recognition, extractive and cloze-style question answering, entity typing, and relation classification.
The abstract from the paper is the following:
Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats words and entities in a given text as independent tokens, and outputs contextualized representations of them. Our model is trained using a new pretraining task based on the masked language model of BERT. The task involves predicting randomly masked words and entities in a large entity-annotated corpus retrieved from Wikipedia. We also propose an entity-aware self-attention mechanism that is an extension of the self-attention mechanism of the transformer, and considers the types of tokens (words or entities) when computing attention scores. The proposed model achieves impressive empirical performance on a wide range of entity-related tasks. In particular, it obtains state-of-the-art results on five well-known datasets: Open Entity (entity typing), TACRED (relation classification), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), and SQuAD 1.1 (extractive question answering).
This model was contributed by ikuyamada and nielsr. The original code can be found here.
Usage tips
This implementation is the same as RobertaModel with the addition of entity embeddings as well as an entity-aware self-attention mechanism, which improves performance on tasks involving reasoning about entities.
LUKE treats entities as input tokens; therefore, it takes
entity_ids
,entity_attention_mask
,entity_token_type_ids
andentity_position_ids
as extra input. You can obtain those using LukeTokenizer.LukeTokenizer takes
entities
andentity_spans
(character-based start and end positions of the entities in the input text) as extra input.entities
typically consist of [MASK] entities or Wikipedia entities. The brief description when inputting these entities are as follows:- Inputting [MASK] entities to compute entity representations: The [MASK] entity is used to mask entities to be predicted during pretraining. When LUKE receives the [MASK] entity, it tries to predict the original entity by gathering the information about the entity from the input text. Therefore, the [MASK] entity can be used to address downstream tasks requiring the information of entities in text such as entity typing, relation classification, and named entity recognition.
- Inputting Wikipedia entities to compute knowledge-enhanced token representations: LUKE learns rich information (or knowledge) about Wikipedia entities during pretraining and stores the information in its entity embedding. By using Wikipedia entities as input tokens, LUKE outputs token representations enriched by the information stored in the embeddings of these entities. This is particularly effective for tasks requiring real-world knowledge, such as question answering.
There are three head models for the former use case:
- LukeForEntityClassification, for tasks to classify a single entity in an input text such as entity typing, e.g. the Open Entity dataset. This model places a linear head on top of the output entity representation.
- LukeForEntityPairClassification, for tasks to classify the relationship between two entities such as relation classification, e.g. the TACRED dataset. This model places a linear head on top of the concatenated output representation of the pair of given entities.
- LukeForEntitySpanClassification, for tasks to classify the sequence of entity spans, such as named entity recognition (NER). This model places a linear head on top of the output entity representations. You can address NER using this model by inputting all possible entity spans in the text to the model.
LukeTokenizer has a
task
argument, which enables you to easily create an input to these head models by specifyingtask="entity_classification"
,task="entity_pair_classification"
, ortask="entity_span_classification"
. Please refer to the example code of each head models.
Usage example:
>>> from transformers import LukeTokenizer, LukeModel, LukeForEntityPairClassification
>>> model = LukeModel.from_pretrained("studio-ousia/luke-base")
>>> tokenizer = LukeTokenizer.from_pretrained("studio-ousia/luke-base")
# Example 1: Computing the contextualized entity representation corresponding to the entity mention "BeyoncΓ©"
>>> text = "BeyoncΓ© lives in Los Angeles."
>>> entity_spans = [(0, 7)] # character-based entity span corresponding to "BeyoncΓ©"
>>> inputs = tokenizer(text, entity_spans=entity_spans, add_prefix_space=True, return_tensors="pt")
>>> outputs = model(**inputs)
>>> word_last_hidden_state = outputs.last_hidden_state
>>> entity_last_hidden_state = outputs.entity_last_hidden_state
# Example 2: Inputting Wikipedia entities to obtain enriched contextualized representations
>>> entities = [
... "BeyoncΓ©",
... "Los Angeles",
... ] # Wikipedia entity titles corresponding to the entity mentions "BeyoncΓ©" and "Los Angeles"
>>> entity_spans = [(0, 7), (17, 28)] # character-based entity spans corresponding to "BeyoncΓ©" and "Los Angeles"
>>> inputs = tokenizer(text, entities=entities, entity_spans=entity_spans, add_prefix_space=True, return_tensors="pt")
>>> outputs = model(**inputs)
>>> word_last_hidden_state = outputs.last_hidden_state
>>> entity_last_hidden_state = outputs.entity_last_hidden_state
# Example 3: Classifying the relationship between two entities using LukeForEntityPairClassification head model
>>> model = LukeForEntityPairClassification.from_pretrained("studio-ousia/luke-large-finetuned-tacred")
>>> tokenizer = LukeTokenizer.from_pretrained("studio-ousia/luke-large-finetuned-tacred")
>>> entity_spans = [(0, 7), (17, 28)] # character-based entity spans corresponding to "BeyoncΓ©" and "Los Angeles"
>>> inputs = tokenizer(text, entity_spans=entity_spans, return_tensors="pt")
>>> outputs = model(**inputs)
>>> logits = outputs.logits
>>> predicted_class_idx = int(logits[0].argmax())
>>> print("Predicted class:", model.config.id2label[predicted_class_idx])
Resources
- A demo notebook on how to fine-tune [LukeForEntityPairClassification](/docs/transformers/v4.47.0/en/model_doc/luke#transformers.LukeForEntityPairClassification) for relation classification
- Notebooks showcasing how you to reproduce the results as reported in the paper with the HuggingFace implementation of LUKE
- Text classification task guide
- Token classification task guide
- Question answering task guide
- Masked language modeling task guide
- Multiple choice task guide
LukeConfig
class transformers.LukeConfig
< source >( vocab_size = 50267 entity_vocab_size = 500000 hidden_size = 768 entity_emb_size = 256 num_hidden_layers = 12 num_attention_heads = 12 intermediate_size = 3072 hidden_act = 'gelu' hidden_dropout_prob = 0.1 attention_probs_dropout_prob = 0.1 max_position_embeddings = 512 type_vocab_size = 2 initializer_range = 0.02 layer_norm_eps = 1e-12 use_entity_aware_attention = True classifier_dropout = None pad_token_id = 1 bos_token_id = 0 eos_token_id = 2 **kwargs )
Parameters
- vocab_size (
int
, optional, defaults to 50267) — Vocabulary size of the LUKE model. Defines the number of different tokens that can be represented by theinputs_ids
passed when calling LukeModel. - entity_vocab_size (
int
, optional, defaults to 500000) — Entity vocabulary size of the LUKE model. Defines the number of different entities that can be represented by theentity_ids
passed when calling LukeModel. - hidden_size (
int
, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer. - entity_emb_size (
int
, optional, defaults to 256) — The number of dimensions of the entity embedding. - num_hidden_layers (
int
, optional, defaults to 12) — Number of hidden layers in the Transformer encoder. - num_attention_heads (
int
, optional, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder. - intermediate_size (
int
, optional, defaults to 3072) — Dimensionality of the “intermediate” (often named feed-forward) layer in the Transformer encoder. - hidden_act (
str
orCallable
, optional, defaults to"gelu"
) — The non-linear activation function (function or string) in the encoder and pooler. If string,"gelu"
,"relu"
,"silu"
and"gelu_new"
are supported. - hidden_dropout_prob (
float
, optional, defaults to 0.1) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. - attention_probs_dropout_prob (
float
, optional, defaults to 0.1) — The dropout ratio for the attention probabilities. - max_position_embeddings (
int
, optional, defaults to 512) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). - type_vocab_size (
int
, optional, defaults to 2) — The vocabulary size of thetoken_type_ids
passed when calling LukeModel. - initializer_range (
float
, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. - layer_norm_eps (
float
, optional, defaults to 1e-12) — The epsilon used by the layer normalization layers. - use_entity_aware_attention (
bool
, optional, defaults toTrue
) — Whether or not the model should use the entity-aware self-attention mechanism proposed in LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention (Yamada et al.). - classifier_dropout (
float
, optional) — The dropout ratio for the classification head. - pad_token_id (
int
, optional, defaults to 1) — Padding token id. - bos_token_id (
int
, optional, defaults to 0) — Beginning of stream token id. - eos_token_id (
int
, optional, defaults to 2) — End of stream token id.
This is the configuration class to store the configuration of a LukeModel. It is used to instantiate a LUKE model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the LUKE studio-ousia/luke-base architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
LukeTokenizer
class transformers.LukeTokenizer
< source >( vocab_file merges_file entity_vocab_file task = None max_entity_length = 32 max_mention_length = 30 entity_token_1 = '<ent>' entity_token_2 = '<ent2>' entity_unk_token = '[UNK]' entity_pad_token = '[PAD]' entity_mask_token = '[MASK]' entity_mask2_token = '[MASK2]' errors = 'replace' bos_token = '<s>' eos_token = '</s>' sep_token = '</s>' cls_token = '<s>' unk_token = '<unk>' pad_token = '<pad>' mask_token = '<mask>' add_prefix_space = False **kwargs )
Parameters
- vocab_file (
str
) — Path to the vocabulary file. - merges_file (
str
) — Path to the merges file. - entity_vocab_file (
str
) — Path to the entity vocabulary file. - task (
str
, optional) — Task for which you want to prepare sequences. One of"entity_classification"
,"entity_pair_classification"
, or"entity_span_classification"
. If you specify this argument, the entity sequence is automatically created based on the given entity span(s). - max_entity_length (
int
, optional, defaults to 32) — The maximum length ofentity_ids
. - max_mention_length (
int
, optional, defaults to 30) — The maximum number of tokens inside an entity span. - entity_token_1 (
str
, optional, defaults to<ent>
) — The special token used to represent an entity span in a word token sequence. This token is only used whentask
is set to"entity_classification"
or"entity_pair_classification"
. - entity_token_2 (
str
, optional, defaults to<ent2>
) — The special token used to represent an entity span in a word token sequence. This token is only used whentask
is set to"entity_pair_classification"
. - errors (
str
, optional, defaults to"replace"
) — Paradigm to follow when decoding bytes to UTF-8. See bytes.decode for more information. - bos_token (
str
, optional, defaults to"<s>"
) — The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.When building a sequence using special tokens, this is not the token that is used for the beginning of sequence. The token used is the
cls_token
. - eos_token (
str
, optional, defaults to"</s>"
) — The end of sequence token.When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the
sep_token
. - sep_token (
str
, optional, defaults to"</s>"
) — The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens. - cls_token (
str
, optional, defaults to"<s>"
) — The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens. - unk_token (
str
, optional, defaults to"<unk>"
) — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead. - pad_token (
str
, optional, defaults to"<pad>"
) — The token used for padding, for example when batching sequences of different lengths. - mask_token (
str
, optional, defaults to"<mask>"
) — The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict. - add_prefix_space (
bool
, optional, defaults toFalse
) — Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (LUKE tokenizer detect beginning of words by the preceding space).
Constructs a LUKE tokenizer, derived from the GPT-2 tokenizer, using byte-level Byte-Pair-Encoding.
This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
be encoded differently whether it is at the beginning of the sentence (without space) or not:
>>> from transformers import LukeTokenizer
>>> tokenizer = LukeTokenizer.from_pretrained("studio-ousia/luke-base")
>>> tokenizer("Hello world")["input_ids"]
[0, 31414, 232, 2]
>>> tokenizer(" Hello world")["input_ids"]
[0, 20920, 232, 2]
You can get around that behavior by passing add_prefix_space=True
when instantiating this tokenizer or when you
call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.
When used with is_split_into_words=True
, this tokenizer will add a space before each word (even the first one).
This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods. It also creates entity sequences, namely
entity_ids
, entity_attention_mask
, entity_token_type_ids
, and entity_position_ids
to be used by the LUKE
model.
__call__
< source >( text: typing.Union[str, typing.List[str]] text_pair: typing.Union[str, typing.List[str], NoneType] = None entity_spans: typing.Union[typing.List[typing.Tuple[int, int]], typing.List[typing.List[typing.Tuple[int, int]]], NoneType] = None entity_spans_pair: typing.Union[typing.List[typing.Tuple[int, int]], typing.List[typing.List[typing.Tuple[int, int]]], NoneType] = None entities: typing.Union[typing.List[str], typing.List[typing.List[str]], NoneType] = None entities_pair: typing.Union[typing.List[str], typing.List[typing.List[str]], NoneType] = None add_special_tokens: bool = True padding: typing.Union[bool, str, transformers.utils.generic.PaddingStrategy] = False truncation: typing.Union[bool, str, transformers.tokenization_utils_base.TruncationStrategy] = None max_length: typing.Optional[int] = None max_entity_length: typing.Optional[int] = None stride: int = 0 is_split_into_words: typing.Optional[bool] = False pad_to_multiple_of: typing.Optional[int] = None padding_side: typing.Optional[bool] = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None return_token_type_ids: typing.Optional[bool] = None return_attention_mask: typing.Optional[bool] = None return_overflowing_tokens: bool = False return_special_tokens_mask: bool = False return_offsets_mapping: bool = False return_length: bool = False verbose: bool = True **kwargs ) β BatchEncoding
Parameters
- text (
str
,List[str]
,List[List[str]]
) — The sequence or batch of sequences to be encoded. Each sequence must be a string. Note that this tokenizer does not support tokenization based on pretokenized strings. - text_pair (
str
,List[str]
,List[List[str]]
) — The sequence or batch of sequences to be encoded. Each sequence must be a string. Note that this tokenizer does not support tokenization based on pretokenized strings. - entity_spans (
List[Tuple[int, int]]
,List[List[Tuple[int, int]]]
, optional) — The sequence or batch of sequences of entity spans to be encoded. Each sequence consists of tuples each with two integers denoting character-based start and end positions of entities. If you specify"entity_classification"
or"entity_pair_classification"
as thetask
argument in the constructor, the length of each sequence must be 1 or 2, respectively. If you specifyentities
, the length of each sequence must be equal to the length of each sequence ofentities
. - entity_spans_pair (
List[Tuple[int, int]]
,List[List[Tuple[int, int]]]
, optional) — The sequence or batch of sequences of entity spans to be encoded. Each sequence consists of tuples each with two integers denoting character-based start and end positions of entities. If you specify thetask
argument in the constructor, this argument is ignored. If you specifyentities_pair
, the length of each sequence must be equal to the length of each sequence ofentities_pair
. - entities (
List[str]
,List[List[str]]
, optional) — The sequence or batch of sequences of entities to be encoded. Each sequence consists of strings representing entities, i.e., special entities (e.g., [MASK]) or entity titles of Wikipedia (e.g., Los Angeles). This argument is ignored if you specify thetask
argument in the constructor. The length of each sequence must be equal to the length of each sequence ofentity_spans
. If you specifyentity_spans
without specifying this argument, the entity sequence or the batch of entity sequences is automatically constructed by filling it with the [MASK] entity. - entities_pair (
List[str]
,List[List[str]]
, optional) — The sequence or batch of sequences of entities to be encoded. Each sequence consists of strings representing entities, i.e., special entities (e.g., [MASK]) or entity titles of Wikipedia (e.g., Los Angeles). This argument is ignored if you specify thetask
argument in the constructor. The length of each sequence must be equal to the length of each sequence ofentity_spans_pair
. If you specifyentity_spans_pair
without specifying this argument, the entity sequence or the batch of entity sequences is automatically constructed by filling it with the [MASK] entity. - max_entity_length (
int
, optional) — The maximum length ofentity_ids
. - add_special_tokens (
bool
, optional, defaults toTrue
) — Whether or not to add special tokens when encoding the sequences. This will use the underlyingPretrainedTokenizerBase.build_inputs_with_special_tokens
function, which defines which tokens are automatically added to the input ids. This is usefull if you want to addbos
oreos
tokens automatically. - padding (
bool
,str
or PaddingStrategy, optional, defaults toFalse
) — Activates and controls padding. Accepts the following values:True
or'longest'
: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided).'max_length'
: Pad to a maximum length specified with the argumentmax_length
or to the maximum acceptable input length for the model if that argument is not provided.False
or'do_not_pad'
(default): No padding (i.e., can output a batch with sequences of different lengths).
- truncation (
bool
,str
or TruncationStrategy, optional, defaults toFalse
) — Activates and controls truncation. Accepts the following values:True
or'longest_first'
: Truncate to a maximum length specified with the argumentmax_length
or to the maximum acceptable input length for the model if that argument is not provided. This will truncate token by token, removing a token from the longest sequence in the pair if a pair of sequences (or a batch of pairs) is provided.'only_first'
: Truncate to a maximum length specified with the argumentmax_length
or to the maximum acceptable input length for the model if that argument is not provided. This will only truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided.'only_second'
: Truncate to a maximum length specified with the argumentmax_length
or to the maximum acceptable input length for the model if that argument is not provided. This will only truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided.False
or'do_not_truncate'
(default): No truncation (i.e., can output batch with sequence lengths greater than the model maximum admissible input size).
- max_length (
int
, optional) — Controls the maximum length to use by one of the truncation/padding parameters.If left unset or set to
None
, this will use the predefined model maximum length if a maximum length is required by one of the truncation/padding parameters. If the model has no specific maximum input length (like XLNet) truncation/padding to a maximum length will be deactivated. - stride (
int
, optional, defaults to 0) — If set to a number along withmax_length
, the overflowing tokens returned whenreturn_overflowing_tokens=True
will contain some tokens from the end of the truncated sequence returned to provide some overlap between truncated and overflowing sequences. The value of this argument defines the number of overlapping tokens. - is_split_into_words (
bool
, optional, defaults toFalse
) — Whether or not the input is already pre-tokenized (e.g., split into words). If set toTrue
, the tokenizer assumes the input is already split into words (for instance, by splitting it on whitespace) which it will tokenize. This is useful for NER or token classification. - pad_to_multiple_of (
int
, optional) — If set will pad the sequence to a multiple of the provided value. Requirespadding
to be activated. This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability>= 7.5
(Volta). - padding_side (
str
, optional) — The side on which the model should have padding applied. Should be selected between [‘right’, ‘left’]. Default value is picked from the class attribute of the same name. - return_tensors (
str
or TensorType, optional) — If set, will return tensors instead of list of python integers. Acceptable values are:'tf'
: Return TensorFlowtf.constant
objects.'pt'
: Return PyTorchtorch.Tensor
objects.'np'
: Return Numpynp.ndarray
objects.
- return_token_type_ids (
bool
, optional) — Whether to return token type IDs. If left to the default, will return the token type IDs according to the specific tokenizer’s default, defined by thereturn_outputs
attribute. - return_attention_mask (
bool
, optional) — Whether to return the attention mask. If left to the default, will return the attention mask according to the specific tokenizer’s default, defined by thereturn_outputs
attribute. - return_overflowing_tokens (
bool
, optional, defaults toFalse
) — Whether or not to return overflowing token sequences. If a pair of sequences of input ids (or a batch of pairs) is provided withtruncation_strategy = longest_first
orTrue
, an error is raised instead of returning overflowing tokens. - return_special_tokens_mask (
bool
, optional, defaults toFalse
) — Whether or not to return special tokens mask information. - return_offsets_mapping (
bool
, optional, defaults toFalse
) — Whether or not to return(char_start, char_end)
for each token.This is only available on fast tokenizers inheriting from PreTrainedTokenizerFast, if using Python’s tokenizer, this method will raise
NotImplementedError
. - return_length (
bool
, optional, defaults toFalse
) — Whether or not to return the lengths of the encoded inputs. - verbose (
bool
, optional, defaults toTrue
) — Whether or not to print more information and warnings. - **kwargs — passed to the
self.tokenize()
method
Returns
A BatchEncoding with the following fields:
-
input_ids β List of token ids to be fed to a model.
-
token_type_ids β List of token type ids to be fed to a model (when
return_token_type_ids=True
or if βtoken_type_idsβ is inself.model_input_names
). -
attention_mask β List of indices specifying which tokens should be attended to by the model (when
return_attention_mask=True
or if βattention_maskβ is inself.model_input_names
). -
entity_ids β List of entity ids to be fed to a model.
-
entity_position_ids β List of entity positions in the input sequence to be fed to a model.
-
entity_token_type_ids β List of entity token type ids to be fed to a model (when
return_token_type_ids=True
or if βentity_token_type_idsβ is inself.model_input_names
). -
entity_attention_mask β List of indices specifying which entities should be attended to by the model (when
return_attention_mask=True
or if βentity_attention_maskβ is inself.model_input_names
). -
entity_start_positions β List of the start positions of entities in the word token sequence (when
task="entity_span_classification"
). -
entity_end_positions β List of the end positions of entities in the word token sequence (when
task="entity_span_classification"
). -
overflowing_tokens β List of overflowing tokens sequences (when a
max_length
is specified andreturn_overflowing_tokens=True
). -
num_truncated_tokens β Number of tokens truncated (when a
max_length
is specified andreturn_overflowing_tokens=True
). -
special_tokens_mask β List of 0s and 1s, with 1 specifying added special tokens and 0 specifying regular sequence tokens (when
add_special_tokens=True
andreturn_special_tokens_mask=True
). -
length β The length of the inputs (when
return_length=True
)
Main method to tokenize and prepare for the model one or several sequence(s) or one or several pair(s) of sequences, depending on the task you want to prepare them for.
LukeModel
class transformers.LukeModel
< source >( config: LukeConfig add_pooling_layer: bool = True )
Parameters
- config (LukeConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The bare LUKE model transformer outputting raw hidden-states for both word tokens and entities without any specific head on top.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None entity_ids: typing.Optional[torch.LongTensor] = None entity_attention_mask: typing.Optional[torch.FloatTensor] = None entity_token_type_ids: typing.Optional[torch.LongTensor] = None entity_position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) β transformers.models.luke.modeling_luke.BaseLukeModelOutputWithPooling
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
- position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - entity_ids (
torch.LongTensor
of shape(batch_size, entity_length)
) — Indices of entity tokens in the entity vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- entity_attention_mask (
torch.FloatTensor
of shape(batch_size, entity_length)
, optional) — Mask to avoid performing attention on padding entity token indices. Mask values selected in[0, 1]
:- 1 for entity tokens that are not masked,
- 0 for entity tokens that are masked.
- entity_token_type_ids (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Segment token indices to indicate first and second portions of the entity token inputs. Indices are selected in[0, 1]
:- 0 corresponds to a portion A entity token,
- 1 corresponds to a portion B entity token.
- entity_position_ids (
torch.LongTensor
of shape(batch_size, entity_length, max_mention_length)
, optional) — Indices of positions of each input entity in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.models.luke.modeling_luke.BaseLukeModelOutputWithPooling
or tuple(torch.FloatTensor)
A transformers.models.luke.modeling_luke.BaseLukeModelOutputWithPooling
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (LukeConfig) and inputs.
- last_hidden_state (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
) β Sequence of hidden-states at the output of the last layer of the model. - entity_last_hidden_state (
torch.FloatTensor
of shape(batch_size, entity_length, hidden_size)
) β Sequence of entity hidden-states at the output of the last layer of the model. - pooler_output (
torch.FloatTensor
of shape(batch_size, hidden_size)
) β Last layer hidden-state of the first token of the sequence (classification token) further processed by a Linear layer and a Tanh activation function. - hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - entity_hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, entity_length, hidden_size)
. Entity hidden-states of the model at the output of each layer plus the initial entity embedding outputs. - attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length + entity_length, sequence_length + entity_length)
. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The LukeModel forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Examples:
>>> from transformers import AutoTokenizer, LukeModel
>>> tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-base")
>>> model = LukeModel.from_pretrained("studio-ousia/luke-base")
# Compute the contextualized entity representation corresponding to the entity mention "BeyoncΓ©"
>>> text = "BeyoncΓ© lives in Los Angeles."
>>> entity_spans = [(0, 7)] # character-based entity span corresponding to "BeyoncΓ©"
>>> encoding = tokenizer(text, entity_spans=entity_spans, add_prefix_space=True, return_tensors="pt")
>>> outputs = model(**encoding)
>>> word_last_hidden_state = outputs.last_hidden_state
>>> entity_last_hidden_state = outputs.entity_last_hidden_state
# Input Wikipedia entities to obtain enriched contextualized representations of word tokens
>>> text = "BeyoncΓ© lives in Los Angeles."
>>> entities = [
... "BeyoncΓ©",
... "Los Angeles",
... ] # Wikipedia entity titles corresponding to the entity mentions "BeyoncΓ©" and "Los Angeles"
>>> entity_spans = [
... (0, 7),
... (17, 28),
... ] # character-based entity spans corresponding to "BeyoncΓ©" and "Los Angeles"
>>> encoding = tokenizer(
... text, entities=entities, entity_spans=entity_spans, add_prefix_space=True, return_tensors="pt"
... )
>>> outputs = model(**encoding)
>>> word_last_hidden_state = outputs.last_hidden_state
>>> entity_last_hidden_state = outputs.entity_last_hidden_state
LukeForMaskedLM
class transformers.LukeForMaskedLM
< source >( config )
Parameters
- config (LukeConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The LUKE model with a language modeling head and entity prediction head on top for masked language modeling and masked entity prediction.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None entity_ids: typing.Optional[torch.LongTensor] = None entity_attention_mask: typing.Optional[torch.LongTensor] = None entity_token_type_ids: typing.Optional[torch.LongTensor] = None entity_position_ids: typing.Optional[torch.LongTensor] = None labels: typing.Optional[torch.LongTensor] = None entity_labels: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) β transformers.models.luke.modeling_luke.LukeMaskedLMOutput
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
- position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - entity_ids (
torch.LongTensor
of shape(batch_size, entity_length)
) — Indices of entity tokens in the entity vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- entity_attention_mask (
torch.FloatTensor
of shape(batch_size, entity_length)
, optional) — Mask to avoid performing attention on padding entity token indices. Mask values selected in[0, 1]
:- 1 for entity tokens that are not masked,
- 0 for entity tokens that are masked.
- entity_token_type_ids (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Segment token indices to indicate first and second portions of the entity token inputs. Indices are selected in[0, 1]
:- 0 corresponds to a portion A entity token,
- 1 corresponds to a portion B entity token.
- entity_position_ids (
torch.LongTensor
of shape(batch_size, entity_length, max_mention_length)
, optional) — Indices of positions of each input entity in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Labels for computing the masked language modeling loss. Indices should be in[-100, 0, ..., config.vocab_size]
(seeinput_ids
docstring) Tokens with indices set to-100
are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size]
- entity_labels (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Labels for computing the masked language modeling loss. Indices should be in[-100, 0, ..., config.vocab_size]
(seeinput_ids
docstring) Tokens with indices set to-100
are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size]
Returns
transformers.models.luke.modeling_luke.LukeMaskedLMOutput
or tuple(torch.FloatTensor)
A transformers.models.luke.modeling_luke.LukeMaskedLMOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (LukeConfig) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β The sum of masked language modeling (MLM) loss and entity prediction loss. -
mlm_loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Masked language modeling (MLM) loss. -
mep_loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Masked entity prediction (MEP) loss. -
logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
entity_logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the entity prediction head (scores for each entity vocabulary token before SoftMax). -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the initial embedding outputs.
-
entity_hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, entity_length, hidden_size)
. Entity hidden-states of the model at the output of each layer plus the initial entity embedding outputs. -
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The LukeForMaskedLM forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
LukeForEntityClassification
class transformers.LukeForEntityClassification
< source >( config )
Parameters
- config (LukeConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The LUKE model with a classification head on top (a linear layer on top of the hidden state of the first entity token) for entity classification tasks, such as Open Entity.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None entity_ids: typing.Optional[torch.LongTensor] = None entity_attention_mask: typing.Optional[torch.FloatTensor] = None entity_token_type_ids: typing.Optional[torch.LongTensor] = None entity_position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) β transformers.models.luke.modeling_luke.EntityClassificationOutput
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
- position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - entity_ids (
torch.LongTensor
of shape(batch_size, entity_length)
) — Indices of entity tokens in the entity vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- entity_attention_mask (
torch.FloatTensor
of shape(batch_size, entity_length)
, optional) — Mask to avoid performing attention on padding entity token indices. Mask values selected in[0, 1]
:- 1 for entity tokens that are not masked,
- 0 for entity tokens that are masked.
- entity_token_type_ids (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Segment token indices to indicate first and second portions of the entity token inputs. Indices are selected in[0, 1]
:- 0 corresponds to a portion A entity token,
- 1 corresponds to a portion B entity token.
- entity_position_ids (
torch.LongTensor
of shape(batch_size, entity_length, max_mention_length)
, optional) — Indices of positions of each input entity in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensor
of shape(batch_size,)
or(batch_size, num_labels)
, optional) — Labels for computing the classification loss. If the shape is(batch_size,)
, the cross entropy loss is used for the single-label classification. In this case, labels should contain the indices that should be in[0, ..., config.num_labels - 1]
. If the shape is(batch_size, num_labels)
, the binary cross entropy loss is used for the multi-label classification. In this case, labels should only contain[0, 1]
, where 0 and 1 indicate false and true, respectively.
Returns
transformers.models.luke.modeling_luke.EntityClassificationOutput
or tuple(torch.FloatTensor)
A transformers.models.luke.modeling_luke.EntityClassificationOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (LukeConfig) and inputs.
- loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Classification loss. - logits (
torch.FloatTensor
of shape(batch_size, config.num_labels)
) β Classification scores (before SoftMax). - hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - entity_hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, entity_length, hidden_size)
. Entity hidden-states of the model at the output of each layer plus the initial entity embedding outputs. - attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The LukeForEntityClassification forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Examples:
>>> from transformers import AutoTokenizer, LukeForEntityClassification
>>> tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-large-finetuned-open-entity")
>>> model = LukeForEntityClassification.from_pretrained("studio-ousia/luke-large-finetuned-open-entity")
>>> text = "BeyoncΓ© lives in Los Angeles."
>>> entity_spans = [(0, 7)] # character-based entity span corresponding to "BeyoncΓ©"
>>> inputs = tokenizer(text, entity_spans=entity_spans, return_tensors="pt")
>>> outputs = model(**inputs)
>>> logits = outputs.logits
>>> predicted_class_idx = logits.argmax(-1).item()
>>> print("Predicted class:", model.config.id2label[predicted_class_idx])
Predicted class: person
LukeForEntityPairClassification
class transformers.LukeForEntityPairClassification
< source >( config )
Parameters
- config (LukeConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The LUKE model with a classification head on top (a linear layer on top of the hidden states of the two entity tokens) for entity pair classification tasks, such as TACRED.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None entity_ids: typing.Optional[torch.LongTensor] = None entity_attention_mask: typing.Optional[torch.FloatTensor] = None entity_token_type_ids: typing.Optional[torch.LongTensor] = None entity_position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) β transformers.models.luke.modeling_luke.EntityPairClassificationOutput
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
- position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - entity_ids (
torch.LongTensor
of shape(batch_size, entity_length)
) — Indices of entity tokens in the entity vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- entity_attention_mask (
torch.FloatTensor
of shape(batch_size, entity_length)
, optional) — Mask to avoid performing attention on padding entity token indices. Mask values selected in[0, 1]
:- 1 for entity tokens that are not masked,
- 0 for entity tokens that are masked.
- entity_token_type_ids (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Segment token indices to indicate first and second portions of the entity token inputs. Indices are selected in[0, 1]
:- 0 corresponds to a portion A entity token,
- 1 corresponds to a portion B entity token.
- entity_position_ids (
torch.LongTensor
of shape(batch_size, entity_length, max_mention_length)
, optional) — Indices of positions of each input entity in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensor
of shape(batch_size,)
or(batch_size, num_labels)
, optional) — Labels for computing the classification loss. If the shape is(batch_size,)
, the cross entropy loss is used for the single-label classification. In this case, labels should contain the indices that should be in[0, ..., config.num_labels - 1]
. If the shape is(batch_size, num_labels)
, the binary cross entropy loss is used for the multi-label classification. In this case, labels should only contain[0, 1]
, where 0 and 1 indicate false and true, respectively.
Returns
transformers.models.luke.modeling_luke.EntityPairClassificationOutput
or tuple(torch.FloatTensor)
A transformers.models.luke.modeling_luke.EntityPairClassificationOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (LukeConfig) and inputs.
- loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Classification loss. - logits (
torch.FloatTensor
of shape(batch_size, config.num_labels)
) β Classification scores (before SoftMax). - hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - entity_hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, entity_length, hidden_size)
. Entity hidden-states of the model at the output of each layer plus the initial entity embedding outputs. - attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The LukeForEntityPairClassification forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Examples:
>>> from transformers import AutoTokenizer, LukeForEntityPairClassification
>>> tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-large-finetuned-tacred")
>>> model = LukeForEntityPairClassification.from_pretrained("studio-ousia/luke-large-finetuned-tacred")
>>> text = "BeyoncΓ© lives in Los Angeles."
>>> entity_spans = [
... (0, 7),
... (17, 28),
... ] # character-based entity spans corresponding to "BeyoncΓ©" and "Los Angeles"
>>> inputs = tokenizer(text, entity_spans=entity_spans, return_tensors="pt")
>>> outputs = model(**inputs)
>>> logits = outputs.logits
>>> predicted_class_idx = logits.argmax(-1).item()
>>> print("Predicted class:", model.config.id2label[predicted_class_idx])
Predicted class: per:cities_of_residence
LukeForEntitySpanClassification
class transformers.LukeForEntitySpanClassification
< source >( config )
Parameters
- config (LukeConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The LUKE model with a span classification head on top (a linear layer on top of the hidden states output) for tasks such as named entity recognition.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None entity_ids: typing.Optional[torch.LongTensor] = None entity_attention_mask: typing.Optional[torch.LongTensor] = None entity_token_type_ids: typing.Optional[torch.LongTensor] = None entity_position_ids: typing.Optional[torch.LongTensor] = None entity_start_positions: typing.Optional[torch.LongTensor] = None entity_end_positions: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) β transformers.models.luke.modeling_luke.EntitySpanClassificationOutput
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
- position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - entity_ids (
torch.LongTensor
of shape(batch_size, entity_length)
) — Indices of entity tokens in the entity vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- entity_attention_mask (
torch.FloatTensor
of shape(batch_size, entity_length)
, optional) — Mask to avoid performing attention on padding entity token indices. Mask values selected in[0, 1]
:- 1 for entity tokens that are not masked,
- 0 for entity tokens that are masked.
- entity_token_type_ids (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Segment token indices to indicate first and second portions of the entity token inputs. Indices are selected in[0, 1]
:- 0 corresponds to a portion A entity token,
- 1 corresponds to a portion B entity token.
- entity_position_ids (
torch.LongTensor
of shape(batch_size, entity_length, max_mention_length)
, optional) — Indices of positions of each input entity in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - entity_start_positions (
torch.LongTensor
) — The start positions of entities in the word token sequence. - entity_end_positions (
torch.LongTensor
) — The end positions of entities in the word token sequence. - labels (
torch.LongTensor
of shape(batch_size, entity_length)
or(batch_size, entity_length, num_labels)
, optional) — Labels for computing the classification loss. If the shape is(batch_size, entity_length)
, the cross entropy loss is used for the single-label classification. In this case, labels should contain the indices that should be in[0, ..., config.num_labels - 1]
. If the shape is(batch_size, entity_length, num_labels)
, the binary cross entropy loss is used for the multi-label classification. In this case, labels should only contain[0, 1]
, where 0 and 1 indicate false and true, respectively.
Returns
transformers.models.luke.modeling_luke.EntitySpanClassificationOutput
or tuple(torch.FloatTensor)
A transformers.models.luke.modeling_luke.EntitySpanClassificationOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (LukeConfig) and inputs.
- loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Classification loss. - logits (
torch.FloatTensor
of shape(batch_size, entity_length, config.num_labels)
) β Classification scores (before SoftMax). - hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
. Hidden-states of the model at the output of each layer plus the initial embedding outputs. - entity_hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, entity_length, hidden_size)
. Entity hidden-states of the model at the output of each layer plus the initial entity embedding outputs. - attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The LukeForEntitySpanClassification forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Examples:
>>> from transformers import AutoTokenizer, LukeForEntitySpanClassification
>>> tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-large-finetuned-conll-2003")
>>> model = LukeForEntitySpanClassification.from_pretrained("studio-ousia/luke-large-finetuned-conll-2003")
>>> text = "BeyoncΓ© lives in Los Angeles"
# List all possible entity spans in the text
>>> word_start_positions = [0, 8, 14, 17, 21] # character-based start positions of word tokens
>>> word_end_positions = [7, 13, 16, 20, 28] # character-based end positions of word tokens
>>> entity_spans = []
>>> for i, start_pos in enumerate(word_start_positions):
... for end_pos in word_end_positions[i:]:
... entity_spans.append((start_pos, end_pos))
>>> inputs = tokenizer(text, entity_spans=entity_spans, return_tensors="pt")
>>> outputs = model(**inputs)
>>> logits = outputs.logits
>>> predicted_class_indices = logits.argmax(-1).squeeze().tolist()
>>> for span, predicted_class_idx in zip(entity_spans, predicted_class_indices):
... if predicted_class_idx != 0:
... print(text[span[0] : span[1]], model.config.id2label[predicted_class_idx])
BeyoncΓ© PER
Los Angeles LOC
LukeForSequenceClassification
class transformers.LukeForSequenceClassification
< source >( config )
Parameters
- config (LukeConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The LUKE Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None entity_ids: typing.Optional[torch.LongTensor] = None entity_attention_mask: typing.Optional[torch.FloatTensor] = None entity_token_type_ids: typing.Optional[torch.LongTensor] = None entity_position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) β transformers.models.luke.modeling_luke.LukeSequenceClassifierOutput
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
- position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - entity_ids (
torch.LongTensor
of shape(batch_size, entity_length)
) — Indices of entity tokens in the entity vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- entity_attention_mask (
torch.FloatTensor
of shape(batch_size, entity_length)
, optional) — Mask to avoid performing attention on padding entity token indices. Mask values selected in[0, 1]
:- 1 for entity tokens that are not masked,
- 0 for entity tokens that are masked.
- entity_token_type_ids (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Segment token indices to indicate first and second portions of the entity token inputs. Indices are selected in[0, 1]
:- 0 corresponds to a portion A entity token,
- 1 corresponds to a portion B entity token.
- entity_position_ids (
torch.LongTensor
of shape(batch_size, entity_length, max_mention_length)
, optional) — Indices of positions of each input entity in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensor
of shape(batch_size,)
, optional) — Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]
. Ifconfig.num_labels == 1
a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1
a classification loss is computed (Cross-Entropy).
Returns
transformers.models.luke.modeling_luke.LukeSequenceClassifierOutput
or tuple(torch.FloatTensor)
A transformers.models.luke.modeling_luke.LukeSequenceClassifierOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (LukeConfig) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Classification (or regression if config.num_labels==1) loss. -
logits (
torch.FloatTensor
of shape(batch_size, config.num_labels)
) β Classification (or regression if config.num_labels==1) scores (before SoftMax). -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-
entity_hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, entity_length, hidden_size)
. Entity hidden-states of the model at the output of each layer plus the initial entity embedding outputs. -
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The LukeForSequenceClassification forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example of single-label classification:
>>> import torch
>>> from transformers import AutoTokenizer, LukeForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-base")
>>> model = LukeForSequenceClassification.from_pretrained("studio-ousia/luke-base")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_class_id = logits.argmax().item()
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = LukeForSequenceClassification.from_pretrained("studio-ousia/luke-base", num_labels=num_labels)
>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).loss
Example of multi-label classification:
>>> import torch
>>> from transformers import AutoTokenizer, LukeForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-base")
>>> model = LukeForSequenceClassification.from_pretrained("studio-ousia/luke-base", problem_type="multi_label_classification")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = LukeForSequenceClassification.from_pretrained(
... "studio-ousia/luke-base", num_labels=num_labels, problem_type="multi_label_classification"
... )
>>> labels = torch.sum(
... torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).loss
LukeForMultipleChoice
class transformers.LukeForMultipleChoice
< source >( config )
Parameters
- config (LukeConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The LUKE Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None entity_ids: typing.Optional[torch.LongTensor] = None entity_attention_mask: typing.Optional[torch.FloatTensor] = None entity_token_type_ids: typing.Optional[torch.LongTensor] = None entity_position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) β transformers.models.luke.modeling_luke.LukeMultipleChoiceModelOutput
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, num_choices, sequence_length)
) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensor
of shape(batch_size, num_choices, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- token_type_ids (
torch.LongTensor
of shape(batch_size, num_choices, sequence_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
- position_ids (
torch.LongTensor
of shape(batch_size, num_choices, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - entity_ids (
torch.LongTensor
of shape(batch_size, entity_length)
) — Indices of entity tokens in the entity vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- entity_attention_mask (
torch.FloatTensor
of shape(batch_size, entity_length)
, optional) — Mask to avoid performing attention on padding entity token indices. Mask values selected in[0, 1]
:- 1 for entity tokens that are not masked,
- 0 for entity tokens that are masked.
- entity_token_type_ids (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Segment token indices to indicate first and second portions of the entity token inputs. Indices are selected in[0, 1]
:- 0 corresponds to a portion A entity token,
- 1 corresponds to a portion B entity token.
- entity_position_ids (
torch.LongTensor
of shape(batch_size, entity_length, max_mention_length)
, optional) — Indices of positions of each input entity in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, num_choices, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensor
of shape(batch_size,)
, optional) — Labels for computing the multiple choice classification loss. Indices should be in[0, ..., num_choices-1]
wherenum_choices
is the size of the second dimension of the input tensors. (Seeinput_ids
above)
Returns
transformers.models.luke.modeling_luke.LukeMultipleChoiceModelOutput
or tuple(torch.FloatTensor)
A transformers.models.luke.modeling_luke.LukeMultipleChoiceModelOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (LukeConfig) and inputs.
-
loss (
torch.FloatTensor
of shape (1,), optional, returned whenlabels
is provided) β Classification loss. -
logits (
torch.FloatTensor
of shape(batch_size, num_choices)
) β num_choices is the second dimension of the input tensors. (see input_ids above).Classification scores (before SoftMax).
-
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-
entity_hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, entity_length, hidden_size)
. Entity hidden-states of the model at the output of each layer plus the initial entity embedding outputs. -
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The LukeForMultipleChoice forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import AutoTokenizer, LukeForMultipleChoice
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-base")
>>> model = LukeForMultipleChoice.from_pretrained("studio-ousia/luke-base")
>>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced."
>>> choice0 = "It is eaten with a fork and a knife."
>>> choice1 = "It is eaten while held in the hand."
>>> labels = torch.tensor(0).unsqueeze(0) # choice0 is correct (according to Wikipedia ;)), batch size 1
>>> encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors="pt", padding=True)
>>> outputs = model(**{k: v.unsqueeze(0) for k, v in encoding.items()}, labels=labels) # batch size is 1
>>> # the linear classifier still needs to be trained
>>> loss = outputs.loss
>>> logits = outputs.logits
LukeForTokenClassification
class transformers.LukeForTokenClassification
< source >( config )
Parameters
- config (LukeConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The LUKE Model with a token classification head on top (a linear layer on top of the hidden-states output). To
solve Named-Entity Recognition (NER) task using LUKE, LukeForEntitySpanClassification
is more suitable than this
class.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.LongTensor] = None entity_ids: typing.Optional[torch.LongTensor] = None entity_attention_mask: typing.Optional[torch.FloatTensor] = None entity_token_type_ids: typing.Optional[torch.LongTensor] = None entity_position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) β transformers.models.luke.modeling_luke.LukeTokenClassifierOutput
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
- position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - entity_ids (
torch.LongTensor
of shape(batch_size, entity_length)
) — Indices of entity tokens in the entity vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- entity_attention_mask (
torch.FloatTensor
of shape(batch_size, entity_length)
, optional) — Mask to avoid performing attention on padding entity token indices. Mask values selected in[0, 1]
:- 1 for entity tokens that are not masked,
- 0 for entity tokens that are masked.
- entity_token_type_ids (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Segment token indices to indicate first and second portions of the entity token inputs. Indices are selected in[0, 1]
:- 0 corresponds to a portion A entity token,
- 1 corresponds to a portion B entity token.
- entity_position_ids (
torch.LongTensor
of shape(batch_size, entity_length, max_mention_length)
, optional) — Indices of positions of each input entity in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensor
of shape(batch_size,)
, optional) — Labels for computing the multiple choice classification loss. Indices should be in[0, ..., num_choices-1]
wherenum_choices
is the size of the second dimension of the input tensors. (Seeinput_ids
above)
Returns
transformers.models.luke.modeling_luke.LukeTokenClassifierOutput
or tuple(torch.FloatTensor)
A transformers.models.luke.modeling_luke.LukeTokenClassifierOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (LukeConfig) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Classification loss. -
logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.num_labels)
) β Classification scores (before SoftMax). -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-
entity_hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, entity_length, hidden_size)
. Entity hidden-states of the model at the output of each layer plus the initial entity embedding outputs. -
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The LukeForTokenClassification forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import AutoTokenizer, LukeForTokenClassification
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-base")
>>> model = LukeForTokenClassification.from_pretrained("studio-ousia/luke-base")
>>> inputs = tokenizer(
... "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt"
... )
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_token_class_ids = logits.argmax(-1)
>>> # Note that tokens are classified rather then input words which means that
>>> # there might be more predicted token classes than words.
>>> # Multiple token classes might account for the same word
>>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
>>> labels = predicted_token_class_ids
>>> loss = model(**inputs, labels=labels).loss
LukeForQuestionAnswering
class transformers.LukeForQuestionAnswering
< source >( config )
Parameters
- config (LukeConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The LUKE Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear
layers on top of the hidden-states output to compute span start logits
and span end logits
).
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None token_type_ids: typing.Optional[torch.LongTensor] = None position_ids: typing.Optional[torch.FloatTensor] = None entity_ids: typing.Optional[torch.LongTensor] = None entity_attention_mask: typing.Optional[torch.FloatTensor] = None entity_token_type_ids: typing.Optional[torch.LongTensor] = None entity_position_ids: typing.Optional[torch.LongTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None start_positions: typing.Optional[torch.LongTensor] = None end_positions: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) β transformers.models.luke.modeling_luke.LukeQuestionAnsweringModelOutput
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) — Indices of input sequence tokens in the vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- attention_mask (
torch.FloatTensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- token_type_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in[0, 1]
:- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
- position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - entity_ids (
torch.LongTensor
of shape(batch_size, entity_length)
) — Indices of entity tokens in the entity vocabulary.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- entity_attention_mask (
torch.FloatTensor
of shape(batch_size, entity_length)
, optional) — Mask to avoid performing attention on padding entity token indices. Mask values selected in[0, 1]
:- 1 for entity tokens that are not masked,
- 0 for entity tokens that are masked.
- entity_token_type_ids (
torch.LongTensor
of shape(batch_size, entity_length)
, optional) — Segment token indices to indicate first and second portions of the entity token inputs. Indices are selected in[0, 1]
:- 0 corresponds to a portion A entity token,
- 1 corresponds to a portion B entity token.
- entity_position_ids (
torch.LongTensor
of shape(batch_size, entity_length, max_mention_length)
, optional) — Indices of positions of each input entity in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - head_mask (
torch.FloatTensor
of shape(num_heads,)
or(num_layers, num_heads)
, optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]
:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - start_positions (
torch.LongTensor
of shape(batch_size,)
, optional) — Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length
). Position outside of the sequence are not taken into account for computing the loss. - end_positions (
torch.LongTensor
of shape(batch_size,)
, optional) — Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length
). Position outside of the sequence are not taken into account for computing the loss.
Returns
transformers.models.luke.modeling_luke.LukeQuestionAnsweringModelOutput
or tuple(torch.FloatTensor)
A transformers.models.luke.modeling_luke.LukeQuestionAnsweringModelOutput
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (LukeConfig) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Total span extraction loss is the sum of a Cross-Entropy for the start and end positions. -
start_logits (
torch.FloatTensor
of shape(batch_size, sequence_length)
) β Span-start scores (before SoftMax). -
end_logits (
torch.FloatTensor
of shape(batch_size, sequence_length)
) β Span-end scores (before SoftMax). -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size)
.Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-
entity_hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(one for the output of the embeddings + one for the output of each layer) of shape(batch_size, entity_length, hidden_size)
. Entity hidden-states of the model at the output of each layer plus the initial entity embedding outputs. -
attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length)
.Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The LukeForQuestionAnswering forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> from transformers import AutoTokenizer, LukeForQuestionAnswering
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-base")
>>> model = LukeForQuestionAnswering.from_pretrained("studio-ousia/luke-base")
>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
>>> inputs = tokenizer(question, text, return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**inputs)
>>> answer_start_index = outputs.start_logits.argmax()
>>> answer_end_index = outputs.end_logits.argmax()
>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
>>> # target is "nice puppet"
>>> target_start_index = torch.tensor([14])
>>> target_end_index = torch.tensor([15])
>>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
>>> loss = outputs.loss