Twitter Roberta Base Dec2021 Tweetner7 Continuous

🚀 tner/twitter-roberta-base-dec2021-tweetner7-continuous

This model is a fine - tuned version of a pre - trained model, designed to address named entity recognition (NER) tasks in the context of Twitter data. It leverages the power of transformers to accurately identify entities in tweets, offering high - precision results across various entity types.

🚀 Quick Start

This model can be used through the tner library. First, install the library via pip:

pip install tner

Since TweetNER7 pre - processes tweets by converting account names and URLs into special formats, we need to process tweets accordingly before running the model prediction. Here is an example:

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/twitter-roberta-base-dec2021-tweetner7-continuous")
model.predict([text_format])

It can be used via the transformers library, but it is not recommended as the CRF layer is not supported at the moment.

✨ Features

Model Fine - Tuning

This model is a fine - tuned version of [tner/twitter - roberta - base - dec2021 - tweetner - 2020](https://huggingface.co/tner/twitter - roberta - base - dec2021 - tweetner - 2020) on the tner/tweetner7 dataset (train_2021 split). The model is first fine - tuned on train_2020 and then continuously fine - tuned on train_2021 via T - NER's hyper - parameter search.

Performance Metrics

• 2021 Test Set Results:

  • F1 (micro): 0.6511305152373794
  • Precision (micro): 0.6512434933487565
  • Recall (micro): 0.6510175763182239
  • F1 (macro): 0.6001624572691789
  • Precision (macro): 0.5998564738871041
  • Recall (macro): 0.6026065175267361

• Per - Entity F1 Score on Test Set:

  • corporation: 0.5055066079295154
  • creative_work: 0.47089601046435575
  • event: 0.4448705656759348
  • group: 0.6124532153793807
  • location: 0.6592689295039165
  • person: 0.8386047352250136
  • product: 0.6695371367061357

• Confidence Intervals for F1 Scores:

  • F1 (micro):
    • 90%: [0.642462096346594, 0.6609916755115764]
    • 95%: [0.6408253162283987, 0.6624122690460243]
  • F1 (macro):
    • 90%: [0.642462096346594, 0.6609916755115764]
    • 95%: [0.6408253162283987, 0.6624122690460243]

Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/twitter - roberta - base - dec2021 - tweetner7 - continuous/raw/main/eval/metric.json) and [metric file of entity span](https://huggingface.co/tner/twitter - roberta - base - dec2021 - tweetner7 - continuous/raw/main/eval/metric_span.json).

🔧 Technical Details

Training Hyperparameters

The following hyperparameters were used during training:

The full configuration can be found at [fine - tuning parameter file](https://huggingface.co/tner/twitter - roberta - base - dec2021 - tweetner7 - continuous/raw/main/trainer_config.json).

📄 License

Reference

If you use the model, please cite the following papers:

• 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",
}