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

此模型是在 tner/tweetner7 数据集（train_random分割）上对 cardiffnlp/twitter-roberta-base-dec2021 进行微调的版本。模型微调是通过 T-NER 的超参数搜索完成的（有关详细信息，请参见存储库）。它在2021年的测试集上取得以下结果：

• F1（微平均）：0.6321284238886395
• 精确度（微平均）：0.6142015706806283
• 召回率（微平均）：0.6511332099907493
• F1（宏平均）：0.583682304736069
• 精确度（宏平均）：0.5654677691354458
• 召回率（宏平均）：0.6047150410746663

测试集上的F1分数的实体细分如下：

• 公司：0.5019685039370079
• 创作作品：0.41401273885350315
• 事件：0.4564727108705458
• 团体：0.5892444737710327
• 地点：0.6486486486486486
• 人物：0.8268075031870332
• 产品：0.6486215538847118

对于F1分数，通过以下Bootstrap方法获得置信区间：

• F1（微平均）：
  • 90%：[0.6245116881258609，0.6411928894306437]
  • 95%：[0.6221686986039963，0.642603475030015]
• F1（宏平均）：
  • 90%：[0.6245116881258609，0.6411928894306437]
  • 95%：[0.6221686986039963，0.642603475030015]

完整的评估结果可以在 metric file of NER 和 metric file of entity span 中找到。

用法

可以通过 tner library 使用此模型。通过pip安装该库。

pip install tner

TweetNER7 预处理了推文，其中账户名称和URL被转换为特殊格式（有关详细信息，请参见数据集页面），因此我们根据此格式处理推文，然后按以下方式运行模型预测。

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])

可以通过transformers库使用它，但是目前不建议使用，因为不支持CRF层。

训练超参数

训练期间使用了以下超参数：

• 数据集：['tner/tweetner7']
• 数据集分割：train_random
• 数据集名称：None
• 本地数据集：None
• 模型：cardiffnlp/twitter-roberta-base-dec2021
• CRF：True
• max_length：128
• epoch：30
• batch_size：32
• lr：0.0001
• 随机种子：0
• 梯度累积步数：1
• 权重衰减：1e-07
• lr_warmup_step_ratio：0.15
• max_grad_norm：1

完整的配置可以在 fine-tuning parameter file 中找到。

参考

如果您使用了这个模型，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",
}