| | --- |
| | datasets: |
| | - tner/tweetner7 |
| | metrics: |
| | - f1 |
| | - precision |
| | - recall |
| | model-index: |
| | - name: tner/roberta-large-tweetner7-2021 |
| | results: |
| | - task: |
| | name: Token Classification |
| | type: token-classification |
| | dataset: |
| | name: tner/tweetner7 |
| | type: tner/tweetner7 |
| | args: tner/tweetner7 |
| | metrics: |
| | - name: F1 (test_2021) |
| | type: f1 |
| | value: 0.6404513989878424 |
| | - name: Precision (test_2021) |
| | type: precision |
| | value: 0.6443872176050568 |
| | - name: Recall (test_2021) |
| | type: recall |
| | value: 0.6365633672525439 |
| | - name: Macro F1 (test_2021) |
| | type: f1_macro |
| | value: 0.5910583983096561 |
| | - name: Macro Precision (test_2021) |
| | type: precision_macro |
| | value: 0.5928837696021392 |
| | - name: Macro Recall (test_2021) |
| | type: recall_macro |
| | value: 0.5900571634271187 |
| | - name: Entity Span F1 (test_2021) |
| | type: f1_entity_span |
| | value: 0.7770796974985457 |
| | - name: Entity Span Precision (test_2020) |
| | type: precision_entity_span |
| | value: 0.7818096687346365 |
| | - name: Entity Span Recall (test_2021) |
| | type: recall_entity_span |
| | value: 0.7724066150109865 |
| | - name: F1 (test_2020) |
| | type: f1 |
| | value: 0.6335644937586686 |
| | - name: Precision (test_2020) |
| | type: precision |
| | value: 0.6805721096543504 |
| | - name: Recall (test_2020) |
| | type: recall |
| | value: 0.5926310326933056 |
| | - name: Macro F1 (test_2020) |
| | type: f1_macro |
| | value: 0.5914520478690088 |
| | - name: Macro Precision (test_2020) |
| | type: precision_macro |
| | value: 0.6370623744887871 |
| | - name: Macro Recall (test_2020) |
| | type: recall_macro |
| | value: 0.5535477989961968 |
| | - name: Entity Span F1 (test_2020) |
| | type: f1_entity_span |
| | value: 0.7436182019977802 |
| | - name: Entity Span Precision (test_2020) |
| | type: precision_entity_span |
| | value: 0.7990459153249851 |
| | - name: Entity Span Recall (test_2020) |
| | type: recall_entity_span |
| | value: 0.6953814218993254 |
| |
|
| | 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" |
| | --- |
| | # tner/roberta-large-tweetner7-2021 |
| |
|
| | This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the |
| | [tner/tweetner7](https://huggingface.co/datasets/tner/tweetner7) dataset (`train_2021` split). |
| | Model fine-tuning is done via [T-NER](https://github.com/asahi417/tner)'s hyper-parameter search (see the repository |
| | for more detail). It achieves the following results on the test set of 2021: |
| | - F1 (micro): 0.6404513989878424 |
| | - Precision (micro): 0.6443872176050568 |
| | - Recall (micro): 0.6365633672525439 |
| | - F1 (macro): 0.5910583983096561 |
| | - Precision (macro): 0.5928837696021392 |
| | - Recall (macro): 0.5900571634271187 |
| |
|
| |
|
| |
|
| | The per-entity breakdown of the F1 score on the test set are below: |
| | - corporation: 0.5058236272878537 |
| | - creative_work: 0.43911917098445596 |
| | - event: 0.46597353497164457 |
| | - group: 0.6068318821165438 |
| | - location: 0.6398910823689584 |
| | - person: 0.8267511177347244 |
| | - product: 0.6530183727034121 |
| | |
| | For F1 scores, the confidence interval is obtained by bootstrap as below: |
| | - F1 (micro): |
| | - 90%: [0.6310532748860292, 0.6500710194412829] |
| | - 95%: [0.6296658889111393, 0.6521427599284435] |
| | - F1 (macro): |
| | - 90%: [0.6310532748860292, 0.6500710194412829] |
| | - 95%: [0.6296658889111393, 0.6521427599284435] |
| | |
| | Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/roberta-large-tweetner7-2021/raw/main/eval/metric.json) |
| | and [metric file of entity span](https://huggingface.co/tner/roberta-large-tweetner7-2021/raw/main/eval/metric_span.json). |
| | |
| | ### Usage |
| | This model can be used through the [tner library](https://github.com/asahi417/tner). Install the library via pip. |
| | ```shell |
| | pip install tner |
| | ``` |
| | [TweetNER7](https://huggingface.co/datasets/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. |
| | |
| | ```python |
| | 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-tweetner7-2021") |
| | 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_2021 |
| | - dataset_name: None |
| | - local_dataset: None |
| | - 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](https://huggingface.co/tner/roberta-large-tweetner7-2021/raw/main/trainer_config.json). |
| |
|
| | ### 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", |
| | } |
| | |
| | ``` |
| |
|
| |
|
| |
|
