Twitter Roberta Base Dec2021 Tweetner7 Random

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

本模型是在 tner/tweetner7 數據集（train_random 劃分）上對 cardiffnlp/twitter-roberta-base-dec2021 進行微調後的版本。模型微調通過 T-NER 的超參數搜索完成（更多細節請參考該倉庫）。

🚀 快速開始

本模型可通過 tner 庫 使用。首先通過 pip 安裝該庫：

pip install tner

TweetNER7 對推文進行了預處理，將賬號名和 URL 轉換為特殊格式（更多細節請參考數據集頁面）。因此，我們需要對推文進行相應處理，然後運行模型預測，示例如下：

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-random")
model.predict([text_format])

該模型也可通過 transformers 庫使用，但由於目前不支持 CRF 層，因此不建議使用。

✨ 主要特性

• 微調模型：基於 cardiffnlp/twitter-roberta-base-dec2021 在 tner/tweetner7 數據集上微調。
• 多指標評估：在測試集上提供了 F1、Precision、Recall 等多種指標的評估結果。
• 支持多種使用方式：可通過 tner 庫 或 transformers 庫使用。

📦 安裝指南

通過 pip 安裝 tner 庫：

pip install tner

💻 使用示例

基礎用法

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-random")
model.predict([text_format])

📚 詳細文檔

評估結果

該模型在 2021 年測試集上取得了以下結果：

• F1 (micro): 0.6321284238886395
• Precision (micro): 0.6142015706806283
• Recall (micro): 0.6511332099907493
• F1 (macro): 0.583682304736069
• Precision (macro): 0.5654677691354458
• Recall (macro): 0.6047150410746663

測試集上 F1 分數的按實體細分結果如下：

• corporation: 0.5019685039370079
• creative_work: 0.41401273885350315
• event: 0.4564727108705458
• group: 0.5892444737710327
• location: 0.6486486486486486
• person: 0.8268075031870332
• product: 0.6486215538847118

對於 F1 分數，通過自助法獲得的置信區間如下：

• F1 (micro):
  • 90%: [0.6245116881258609, 0.6411928894306437]
  • 95%: [0.6221686986039963, 0.642603475030015]
• F1 (macro):
  • 90%: [0.6245116881258609, 0.6411928894306437]
  • 95%: [0.6221686986039963, 0.642603475030015]

完整評估結果可在 NER 指標文件 和 實體跨度指標文件 中查看。

訓練超參數

訓練過程中使用了以下超參數：

完整配置可在 微調參數文件 中查看。

🔧 技術細節

模型微調通過 T-NER 的超參數搜索完成。在訓練過程中，使用了 CRF 層來提升模型性能。同時，對推文進行了預處理，將賬號名和 URL 轉換為特殊格式，以適應 TweetNER7 數據集。

📄 許可證

請參考相關引用文獻的許可證信息。

引用

如果使用該模型，請引用以下文獻：

• 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",
}