from dataclasses import dataclass from typing import Optional, Tuple import torch import torch.nn as nn from transformers import ErnieModel, ErniePreTrainedModel, PretrainedConfig from transformers.file_utils import ModelOutput from .decode_utils import UIEDecoder @dataclass class UIEModelOutput(ModelOutput): """ Output class for outputs of UIE. losses (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided): Total spn extraction losses is the sum of a Cross-Entropy for the start and end positions. start_prob (`torch.FloatTensor` of shape `(batch_size, sequence_length)`): Span-start scores (after Sigmoid). end_prob (`torch.FloatTensor` of shape `(batch_size, sequence_length)`): Span-end scores (after Sigmoid). hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layers, + 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. attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`): Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attention weights after the attention softmax, used to compute the weighted average in the self-attention heads. """ loss: Optional[torch.FloatTensor] = None start_prob: torch.FloatTensor = None end_prob: torch.FloatTensor = None start_positions: torch.FloatTensor = None end_positions: torch.FloatTensor = None hidden_states: Optional[Tuple[torch.FloatTensor]] = None attentions: Optional[Tuple[torch.FloatTensor]] = None class UIEModel(ErniePreTrainedModel, UIEDecoder): """ UIE model based on Bert model. 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](https://pytorch.org/docs/stable/nn.html#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. Parameters: config ([`PretrainedConfig`]): 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 [`~PreTrainedModel.from_pretrained`] method to load the model weights. """ def __init__(self, config: PretrainedConfig): super(UIEModel, self).__init__(config) self.encoder = ErnieModel(config) self.config = config hidden_size = self.config.hidden_size self.linear_start = nn.Linear(hidden_size, 1) self.linear_end = nn.Linear(hidden_size, 1) self.sigmoid = nn.Sigmoid() self.post_init() def forward( self, input_ids: Optional[torch.Tensor] = None, token_type_ids: Optional[torch.Tensor] = None, position_ids: Optional[torch.Tensor] = None, attention_mask: Optional[torch.Tensor] = None, head_mask: Optional[torch.Tensor] = None, inputs_embeds: Optional[torch.Tensor] = None, start_positions: Optional[torch.Tensor] = None, end_positions: Optional[torch.Tensor] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, ) -> UIEModelOutput: """ Args: input_ids (`torch.LongTensor` of shape `({0})`): Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`BertTokenizer`]. See [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input IDs?](../glossary#input-ids) attention_mask (`torch.FloatTensor` of shape `({0})`, *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**. [What are attention masks?](../glossary#attention-mask) token_type_ids (`torch.LongTensor` of shape `({0})`, *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. [What are token type IDs?](../glossary#token-type-ids) position_ids (`torch.LongTensor` of shape `({0})`, *optional*): Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`. [What are position IDs?](../glossary#position-ids) 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**. inputs_embeds (`torch.FloatTensor` of shape `({0}, hidden_size)`, *optional*): Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. 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 outsides 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 outsides of the sequence are not taken into account for computing the loss. output_attentions (`bool`, *optional*): Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. output_hidden_states (`bool`, *optional*): Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. return_dict (`bool`, *optional*): Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple. """ outputs = self.encoder( input_ids=input_ids, token_type_ids=token_type_ids, position_ids=position_ids, attention_mask=attention_mask, head_mask=head_mask, inputs_embeds=inputs_embeds, output_attentions=output_attentions, output_hidden_states=output_hidden_states, ) sequence_output = outputs[0] start_logits = self.linear_start(sequence_output) start_logits = torch.squeeze(start_logits, -1) start_prob = self.sigmoid(start_logits) end_logits = self.linear_end(sequence_output) end_logits = torch.squeeze(end_logits, -1) end_prob = self.sigmoid(end_logits) total_loss = None if start_positions is not None and end_positions is not None: loss_fct = nn.BCELoss() start_loss = loss_fct(start_prob, start_positions) end_loss = loss_fct(end_prob, end_positions) total_loss = (start_loss + end_loss) / 2.0 return UIEModelOutput( loss=total_loss, start_prob=start_prob, end_prob=end_prob, hidden_states=outputs.hidden_states, attentions=outputs.attentions, )