模型简介
模型特点
模型能力
使用案例
🚀 法律BERT:刚从法学院毕业的“布偶秀明星”
Legal-BERT是一系列用于法律领域的BERT模型,旨在助力法律自然语言处理研究、计算法学以及法律科技应用。为了预训练不同版本的Legal-BERT,我们从多个公开资源中收集了12GB不同类型的英文法律文本,涵盖立法、法院判例、合同等多个领域。特定子领域的变体模型(如合同版、欧盟法律版、欧洲人权法院版)和通用的Legal-BERT在特定领域任务中的表现优于直接使用BERT。这是一个轻量级版本的BERT-BASE(大小仅为BERT-BASE的33%),它基于法律数据从头开始预训练,在性能上可与更大的模型相媲美,同时效率更高(大约快4倍),对环境的影响也更小。
🚀 快速开始
加载预训练模型
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("nlpaueb/legal-bert-small-uncased")
model = AutoModel.from_pretrained("nlpaueb/legal-bert-small-uncased")
将Legal-BERT变体用作语言模型
语料库 | 模型 | 掩码标记 | 预测结果 |
---|---|---|---|
BERT-BASE-UNCASED | |||
(合同) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('new', '0.09'), ('current', '0.04'), ('proposed', '0.03'), ('marketing', '0.03'), ('joint', '0.02') |
(欧洲人权法院) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '0.32'), ('rape', '0.22'), ('abuse', '0.14'), ('death', '0.04'), ('violence', '0.03') |
(欧盟法律) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('farm', '0.25'), ('livestock', '0.08'), ('draft', '0.06'), ('domestic', '0.05'), ('wild', '0.05') |
CONTRACTS-BERT-BASE | |||
(合同) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('letter', '0.38'), ('dealer', '0.04'), ('employment', '0.03'), ('award', '0.03'), ('contribution', '0.02') |
(欧洲人权法院) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('death', '0.39'), ('imprisonment', '0.07'), ('contempt', '0.05'), ('being', '0.03'), ('crime', '0.02') |
(欧盟法律) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | (('domestic', '0.18'), ('laboratory', '0.07'), ('household', '0.06'), ('personal', '0.06'), ('the', '0.04') |
EURLEX-BERT-BASE | |||
(合同) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('supply', '0.11'), ('cooperation', '0.08'), ('service', '0.07'), ('licence', '0.07'), ('distribution', '0.05') |
(欧洲人权法院) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '0.66'), ('death', '0.07'), ('imprisonment', '0.07'), ('murder', '0.04'), ('rape', '0.02') |
(欧盟法律) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('live', '0.43'), ('pet', '0.28'), ('certain', '0.05'), ('fur', '0.03'), ('the', '0.02') |
ECHR-BERT-BASE | |||
(合同) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('second', '0.24'), ('latter', '0.10'), ('draft', '0.05'), ('bilateral', '0.05'), ('arbitration', '0.04') |
(欧洲人权法院) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '0.99'), ('death', '0.01'), ('inhuman', '0.00'), ('beating', '0.00'), ('rape', '0.00') |
(欧盟法律) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('pet', '0.17'), ('all', '0.12'), ('slaughtered', '0.10'), ('domestic', '0.07'), ('individual', '0.05') |
LEGAL-BERT-BASE | |||
(合同) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('settlement', '0.26'), ('letter', '0.23'), ('dealer', '0.04'), ('master', '0.02'), ('supplemental', '0.02') |
(欧洲人权法院) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '1.00'), ('detention', '0.00'), ('arrest', '0.00'), ('rape', '0.00'), ('death', '0.00') |
(欧盟法律) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('live', '0.67'), ('beef', '0.17'), ('farm', '0.03'), ('pet', '0.02'), ('dairy', '0.01') |
LEGAL-BERT-SMALL | |||
(合同) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('license', '0.09'), ('transition', '0.08'), ('settlement', '0.04'), ('consent', '0.03'), ('letter', '0.03') |
(欧洲人权法院) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '0.59'), ('pain', '0.05'), ('ptsd', '0.05'), ('death', '0.02'), ('tuberculosis', '0.02') |
(欧盟法律) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('all', '0.08'), ('live', '0.07'), ('certain', '0.07'), ('the', '0.07'), ('farm', '0.05') |
✨ 主要特性
- 专为法律领域设计,基于大规模法律文本数据进行预训练。
- 有多种变体模型,适用于不同的法律子领域,如合同、欧盟法律、欧洲人权法院判例等。
- 轻量级版本效率高,在性能相当的情况下,速度更快且对环境影响小。
📦 预训练语料库
Legal-BERT的预训练语料库包括:
- 116,062份欧盟立法文件,可从EURLEX(http://eur-lex.europa.eu)获取,这是欧盟出版局运营的欧盟法律资源库。
- 61,826份英国立法文件,可从英国立法门户(http://www.legislation.gov.uk)获取。
- 19,867份欧洲法院(ECJ)的判例,同样可从EURLEX获取。
- 12,554份欧洲人权法院(ECHR)的判例,来自HUDOC资源库(http://hudoc.echr.coe.int/eng)。
- 164,141份美国各地法院的判例,托管在Case Law Access Project门户(https://case.law)。
- 76,366份美国合同,来自美国证券交易委员会(SECOM)的EDGAR数据库(https://www.sec.gov/edgar.shtml)。
🔧 预训练细节
- 我们使用Google BERT的GitHub仓库(https://github.com/google-research/bert)中提供的官方代码来训练BERT。
- 我们发布了一个类似于英文BERT-BASE模型(12层、768隐藏层、12头、1.1亿参数)的模型。
- 我们选择遵循相同的训练设置:进行100万步训练,批次大小为256个长度为512的序列,初始学习率为1e - 4。
- 我们能够使用由TensorFlow Research Cloud (TFRC)免费提供的单个Google Cloud TPU v3 - 8,同时还利用了GCP研究信用额度。非常感谢这两个Google项目对我们的支持!
📚 模型列表
模型名称 | 模型路径 | 训练语料库 |
---|---|---|
CONTRACTS-BERT-BASE | nlpaueb/bert-base-uncased-contracts |
美国合同 |
EURLEX-BERT-BASE | nlpaueb/bert-base-uncased-eurlex |
欧盟立法 |
ECHR-BERT-BASE | nlpaueb/bert-base-uncased-echr |
欧洲人权法院判例 |
LEGAL-BERT-BASE * | nlpaueb/legal-bert-base-uncased |
全部 |
LEGAL-BERT-SMALL | nlpaueb/legal-bert-small-uncased |
全部 |
* LEGAL-BERT-BASE是Chalkidis等人(2020)中提到的LEGAL-BERT-SC模型;该模型是在下面提到的法律语料库上从头开始训练的,使用了由在相同语料库上训练的sentence - piece分词器创建的新词汇表。
** 由于很多人对LEGAL-BERT-FP模型(那些基于原始BERT-BASE检查点的模型)表示感兴趣,这些模型已在Archive.org(https://archive.org/details/legal_bert_fp)上发布,因为这些模型是次要的,可能仅对那些希望深入研究Chalkidis等人(2020)中开放性问题的人有吸引力。
📚 下游任务评估
可参考文章“LEGAL-BERT: The Muppets straight out of Law School”中的实验。Chalkidis等人,2020年,(https://aclanthology.org/2020.findings-emnlp.261)
📄 许可证
本项目采用CC BY - SA 4.0许可证。
📖 引用
@inproceedings{chalkidis-etal-2020-legal,
title = "{LEGAL}-{BERT}: The Muppets straight out of Law School",
author = "Chalkidis, Ilias and
Fergadiotis, Manos and
Malakasiotis, Prodromos and
Aletras, Nikolaos and
Androutsopoulos, Ion",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
doi = "10.18653/v1/2020.findings-emnlp.261",
pages = "2898--2904"
}
👥 关于我们
雅典经济与商业大学自然语言处理小组致力于开发让计算机处理和生成自然语言文本的算法、模型和系统。
该小组目前的研究兴趣包括:
- 用于数据库、本体、文档集合和网络的问答系统,特别是生物医学问答。
- 从数据库和本体,特别是语义网络本体中进行自然语言生成。
- 文本分类,包括过滤垃圾邮件和滥用内容。
- 信息提取和观点挖掘,包括法律文本分析和情感分析。
- 用于希腊语的自然语言处理工具,例如解析器和命名实体识别器。
- 自然语言处理中的机器学习,特别是深度学习。
该小组隶属于雅典经济与商业大学信息学系信息处理实验室。
Ilias Chalkidis 代表 雅典经济与商业大学自然语言处理小组
| GitHub: @ilias.chalkidis | Twitter: @KiddoThe2B |



