metadata
datasets:
- tner/tweetner7
metrics:
- f1
- precision
- recall
pipeline_tag: token-classification
widget:
- text: >-
Get the all-analog Classic Vinyl Edition of `Takin' Off` Album from
{@herbiehancock@} via {@bluenoterecords@} link below: {{URL}}
example_title: NER Example 1
base_model: roberta-large
model-index:
- name: tner/roberta-large-tweetner7-selflabel2020
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: tner/tweetner7
type: tner/tweetner7
args: tner/tweetner7
metrics:
- type: f1
value: 0.6455908683974932
name: F1 (test_2021)
- type: precision
value: 0.6254336513443192
name: Precision (test_2021)
- type: recall
value: 0.6670906567992599
name: Recall (test_2021)
- type: f1_macro
value: 0.5962839441412403
name: Macro F1 (test_2021)
- type: precision_macro
value: 0.5727192958380657
name: Macro Precision (test_2021)
- type: recall_macro
value: 0.6267698180905158
name: Macro Recall (test_2021)
- type: f1_entity_span
value: 0.7846231324492194
name: Entity Span F1 (test_2021)
- type: precision_entity_span
value: 0.7600823937554206
name: Entity Span Precision (test_2020)
- type: recall_entity_span
value: 0.8108014340233607
name: Entity Span Recall (test_2021)
- type: f1
value: 0.6589874095901421
name: F1 (test_2020)
- type: precision
value: 0.6810631229235881
name: Precision (test_2020)
- type: recall
value: 0.6382978723404256
name: Recall (test_2020)
- type: f1_macro
value: 0.6185133813760935
name: Macro F1 (test_2020)
- type: precision_macro
value: 0.6351153721439261
name: Macro Precision (test_2020)
- type: recall_macro
value: 0.6085669577041991
name: Macro Recall (test_2020)
- type: f1_entity_span
value: 0.7670865719646207
name: Entity Span F1 (test_2020)
- type: precision_entity_span
value: 0.7932372505543237
name: Entity Span Precision (test_2020)
- type: recall_entity_span
value: 0.7426050856253243
name: Entity Span Recall (test_2020)
tner/roberta-large-tweetner7-selflabel2020
This model is a fine-tuned version of roberta-large on the
tner/tweetner7 dataset (train split). This model is fine-tuned on self-labeled dataset which is the extra_2020 split of the tner/tweetner7 annotated by tner/roberta-large). Please check https://github.com/asahi417/tner/tree/master/examples/tweetner7_paper#model-fine-tuning-self-labeling for more detail of reproducing the model.
Model fine-tuning is done via T-NER's hyper-parameter search (see the repository
for more detail). It achieves the following results on the test set of 2021:
- F1 (micro): 0.6455908683974932
- Precision (micro): 0.6254336513443192
- Recall (micro): 0.6670906567992599
- F1 (macro): 0.5962839441412403
- Precision (macro): 0.5727192958380657
- Recall (macro): 0.6267698180905158
The per-entity breakdown of the F1 score on the test set are below:
- corporation: 0.522762148337596
- creative_work: 0.468235294117647
- event: 0.4446564885496183
- group: 0.6155398587285571
- location: 0.6423718344657197
- person: 0.840225906358171
- product: 0.6401960784313725
For F1 scores, the confidence interval is obtained by bootstrap as below:
- F1 (micro):
- 90%: [0.6371204057050158, 0.6550747724054871]
- 95%: [0.6350657043101348, 0.6568098006368783]
- F1 (macro):
- 90%: [0.6371204057050158, 0.6550747724054871]
- 95%: [0.6350657043101348, 0.6568098006368783]
Full evaluation can be found at metric file of NER and metric file of entity span.
Usage
This model can be used through the tner library. Install the library via pip.
pip install tner
TweetNER7 pre-processed tweets where the account name and URLs are converted into special formats (see the dataset page for more detail), so we process tweets accordingly and then run the model prediction as below.
import re
from urlextract import URLExtract
from tner import TransformersNER
extractor = URLExtract()
def format_tweet(tweet):
# mask web urls
urls = extractor.find_urls(tweet)
for url in urls:
tweet = tweet.replace(url, "{{URL}}")
# format twitter account
tweet = re.sub(r"\b(\s*)(@[\S]+)\b", r'\1{\2@}', tweet)
return tweet
text = "Get the all-analog Classic Vinyl Edition of `Takin' Off` Album from @herbiehancock via @bluenoterecords link below: http://bluenote.lnk.to/AlbumOfTheWeek"
text_format = format_tweet(text)
model = TransformersNER("tner/roberta-large-tweetner7-selflabel2020")
model.predict([text_format])
It can be used via transformers library but it is not recommended as CRF layer is not supported at the moment.
Training hyperparameters
The following hyperparameters were used during training:
- dataset: ['tner/tweetner7']
- dataset_split: train
- dataset_name: None
- local_dataset: {'train': 'tweet_ner/2020.extra.tner/roberta-large-2020.txt', 'validation': 'tweet_ner/2020.dev.txt'}
- model: roberta-large
- crf: True
- max_length: 128
- epoch: 30
- batch_size: 32
- lr: 1e-05
- random_seed: 0
- gradient_accumulation_steps: 1
- weight_decay: 1e-07
- lr_warmup_step_ratio: 0.15
- max_grad_norm: 1
The full configuration can be found at fine-tuning parameter file.
Reference
If you use the model, please cite T-NER paper and TweetNER7 paper.
- T-NER
@inproceedings{ushio-camacho-collados-2021-ner,
title = "{T}-{NER}: An All-Round Python Library for Transformer-based Named Entity Recognition",
author = "Ushio, Asahi and
Camacho-Collados, Jose",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-demos.7",
doi = "10.18653/v1/2021.eacl-demos.7",
pages = "53--62",
abstract = "Language model (LM) pretraining has led to consistent improvements in many NLP downstream tasks, including named entity recognition (NER). In this paper, we present T-NER (Transformer-based Named Entity Recognition), a Python library for NER LM finetuning. In addition to its practical utility, T-NER facilitates the study and investigation of the cross-domain and cross-lingual generalization ability of LMs finetuned on NER. Our library also provides a web app where users can get model predictions interactively for arbitrary text, which facilitates qualitative model evaluation for non-expert programmers. We show the potential of the library by compiling nine public NER datasets into a unified format and evaluating the cross-domain and cross- lingual performance across the datasets. The results from our initial experiments show that in-domain performance is generally competitive across datasets. However, cross-domain generalization is challenging even with a large pretrained LM, which has nevertheless capacity to learn domain-specific features if fine- tuned on a combined dataset. To facilitate future research, we also release all our LM checkpoints via the Hugging Face model hub.",
}
- TweetNER7
@inproceedings{ushio-etal-2022-tweet,
title = "{N}amed {E}ntity {R}ecognition in {T}witter: {A} {D}ataset and {A}nalysis on {S}hort-{T}erm {T}emporal {S}hifts",
author = "Ushio, Asahi and
Neves, Leonardo and
Silva, Vitor and
Barbieri, Francesco. and
Camacho-Collados, Jose",
booktitle = "The 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing",
month = nov,
year = "2022",
address = "Online",
publisher = "Association for Computational Linguistics",
}