LEGAL-BERT：来自法学院的木偶

LEGAL-BERT是用于法律领域的BERT模型系列，旨在辅助法律NLP研究、计算法律和法律技术应用。为了预训练不同的LEGAL-BERT变体，我们从公开资源中收集了12 GB的不同领域（例如立法、法院案例、合同）的英文法律文本。子域变体（CONTRACTS-、EURLEX-、ECHR-）和/或一般LEGAL-BERT在特定领域的任务中表现更好，优于直接使用BERT。这是在欧盟立法上预训练的子域变体。

I. Chalkidis, M. Fergadiotis, P. Malakasiotis, N. Aletras和I. Androutsopoulos。“LEGAL-BERT：来自法学院的木偶”。在Empirical Methods in Natural Language Processing（EMNLP 2020）（短文）的发现中，将在线举行，2020年。（ https://aclanthology.org/2020.findings-emnlp.261 ）

预训练语料库

LEGAL-BERT的预训练语料库包括：

来自EURLEX（ http://eur-lex.europa.eu ）的116,062个欧盟立法文档，公开可用于欧盟出版社的EU法令库。
来自英国立法门户网站（ http://www.legislation.gov.uk ）的61,826个英国立法文档，公开可用。
来自EURLEX的19,867个欧洲法院(European Court of Justice，ECJ)案例。
来自欧洲人权法院（European Court of Human Rights，ECHR）数据库HUDOC的12,554个案例（ http://hudoc.echr.coe.int/eng ）。
来自美国各个法院的164,141个案例，托管在Case Law Access Project门户网站上（ https://case.law ）。
来自美国证券交易委员会（US Securities and Exchange Commission，SECOM）数据库EDGAR的76,366个美国合同（ https://www.sec.gov/edgar.shtml ）。

预训练细节

我们使用Google BERT的GitHub存储库中提供的官方代码进行BERT的训练（ https://github.com/google-research/bert ）。
我们发布了一个与英文BERT-BASE模型（12层，768隐层，12个注意头，110M参数）类似的模型。
我们选择遵循相同的训练设置：100万个训练步骤，每个批次256个长度为512的序列，初始学习率为1e-4。
我们能够使用免费提供的单个Google Cloud TPU v3-8（ TensorFlow Research Cloud (TFRC) ），同时还利用了（ GCP research credits ）。非常感谢这两个Google计划对我们的支持！

模型列表

Model name	Model Path	Training corpora
CONTRACTS-BERT-BASE	nlpaueb/bert-base-uncased-contracts	US contracts
EURLEX-BERT-BASE	nlpaueb/bert-base-uncased-eurlex	EU legislation
ECHR-BERT-BASE	nlpaueb/bert-base-uncased-echr	ECHR cases
LEGAL-BERT-BASE *	nlpaueb/legal-bert-base-uncased	All
LEGAL-BERT-SMALL	nlpaueb/legal-bert-small-uncased	All

*LEGAL-BERT-BASE是Chalkidis等人（2020）中称为LEGAL-BERT-SC的模型；它是在下面提到的法律语料库上使用由句子分割标记器在相同语料库上进行训练的新词汇表从头训练的模型。

**由于许多人对LEGAL-BERT-FP模型（基于原始BERT-BASE检查点的模型）表示兴趣，它们已在Archive.org上发布（ https://archive.org/details/legal_bert_fp ），因为这些模型是辅助模型，可能仅对那些想深入探讨Chalkidis等人（2020）的开放问题的人有兴趣。

加载预训练模型

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("nlpaueb/bert-base-uncased-eurlex")
model = AutoModel.from_pretrained("nlpaueb/bert-base-uncased-eurlex")

将LEGAL-BERT变体用作语言模型

Corpus	Model	Masked token	Predictions
BERT-BASE-UNCASED
(Contracts)	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')
(ECHR)	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')
(EURLEX)	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
(Contracts)	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')
(ECHR)	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')
(EURLEX)	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
(Contracts)	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')
(ECHR)	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')
(EURLEX)	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
(Contracts)	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')
(ECHR)	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')
(EURLEX)	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
(Contracts)	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')
(ECHR)	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')
(EURLEX)	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
(Contracts)	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')
(ECHR)	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')
(EURLEX)	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')

下游任务的评估

请参阅文章“LEGAL-BERT：来自法学院的木偶”。Chalkidis等人，2020年，（ https://aclanthology.org/2020.findings-emnlp.261 ）

作者-出版物

@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

AUEB's Natural Language Processing Group 开发了允许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：

数据库、本体论、文档集合和Web等方面的问答系统，尤其是生物医学问答系统
从数据库和本体生成自然语言，特别是语义Web本体，文本分类，包括过滤垃圾邮件和滥用内容
信息抽取和观点挖掘，包括法律文本分析和情感分析
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

该小组是希腊经济和商业雅典经济学院信息处理实验室的一部分。

Ilias Chalkidis 代表 AUEB's Natural Language Processing Group

| Github： @ilias.chalkidis | Twitter： @KiddoThe2B |

作者:

AUEB NLP Group

数据集大小:

1.32 GB