Roberta Large Tweetner7 All

🚀 tner/roberta-large-tweetner7-all

tner/roberta-large-tweetner7-all 是一个基于 roberta-large 模型在 tner/tweetner7 数据集上微调得到的模型，用于命名实体识别任务。它能有效处理特定格式的推文数据，在相关评估指标上有不错的表现。

✨ 主要特性

• 基于 roberta-large 模型进行微调，在 tner/tweetner7 数据集上有良好表现。
• 支持使用 tner 库调用，方便快捷。
• 提供了详细的评估指标和训练超参数。

📦 安装指南

此模型可通过 tner 库 使用，可通过以下命令安装该库：

pip install tner

💻 使用示例

基础用法

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/roberta-large-tweetner7-all")
model.predict([text_format])

高级用法

暂未提供高级用法示例。

📚 详细文档

数据集和指标

模型结果

该模型在 2021 年测试集上的表现如下：

• F1 (micro): 0.6574551220340903
• Precision (micro): 0.644212629008989
• Recall (micro): 0.6712534690101758
• F1 (macro): 0.6124665667529737
• Precision (macro): 0.6005167968535563
• Recall (macro): 0.625251837701222

各实体的 F1 分数如下：

• corporation: 0.5392156862745098
• creative_work: 0.4760582928521859
• event: 0.4673321234119782
• group: 0.6139798488664987
• location: 0.6707399864222675
• person: 0.8293212669683258
• product: 0.6906187624750498

F1 分数的置信区间（通过自助法获得）如下：

• F1 (micro):
  • 90%: [0.6484148010152769, 0.6672289519134409]
  • 95%: [0.6470100684797441, 0.6689850350992637]
• F1 (macro):
  • 90%: [0.6484148010152769, 0.6672289519134409]
  • 95%: [0.6470100684797441, 0.6689850350992637]

完整评估结果可参考 NER 评估文件 和 实体跨度评估文件。

训练超参数

以下是训练过程中使用的超参数：

• 数据集: ['tner/tweetner7']
• 数据集分割: train_all
• 数据集名称: None
• 本地数据集: None
• 模型: roberta-large
• CRF: True
• 最大长度: 128
• 训练轮数: 30
• 批次大小: 32
• 学习率: 1e-05
• 随机种子: 0
• 梯度累积步数: 1
• 权重衰减: 1e-07
• 学习率热身步数比例: 0.15
• 最大梯度范数: 1

完整配置可参考 微调参数文件。

🔧 技术细节

该模型基于 roberta-large 进行微调，使用了 CRF 层来提升性能。在训练过程中，使用了特定的超参数进行优化，以在 tner/tweetner7 数据集上达到较好的效果。

📄 许可证

文档未提及相关许可证信息。

📖 引用

如果使用该模型，请引用 T-NER 论文和 TweetNER7 论文：

• 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",
}