LEGAL-BERT:脱离法学院的木偶

LEGAL-BERT是用于法律领域的BERT模型系列，旨在辅助法律自然语言处理研究、计算法律和法律科技应用。为了预训练不同变体的LEGAL-BERT，我们从公开可用资源中收集了来自多个领域（包括立法、法庭案例和合同）的12GB多样化的英文法律文本。子领域变体（CONTRACTS-、EURLEX-、ECHR-）和/或通用的LEGAL-BERT在特定领域的任务上表现比直接使用BERT更好。这是在美国合同上预训练的子领域变体。

I. Chalkidis, M. Fergadiotis, P. Malakasiotis, N. Aletras和I. Androutsopoulos. "LEGAL-BERT:脱离法学院的木偶"。在Empirical Methods in Natural Language Processing (EMNLP 2020) (Short Papers)上发表，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 ）公开可用的欧盟立法文件116,062份，这是在欧盟出版办公室运行的EU法律存储库。
来自英国立法门户网站（ http://www.legislation.gov.uk ）公开可用的61,826份英国立法文件。
来自欧洲法院（ECJ）的19,867个案件，也可从EURLEX获得。
来自欧洲人权法院（ECHR）存储库HUDOC的12,554个案件（ http://hudoc.echr.coe.int/eng ）。
来自美国不同法院的164,141个案例，托管在Case Law Access Project门户网站中（ https://case.law ）。
来自美国证券交易委员会（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训练了BERT（ https://github.com/google-research/bert ）。
我们发布了一个与英文BERT-BASE模型相似的模型（12层，768隐藏层，12个头，110M参数）。
我们选择遵循相同的训练设置：100万个训练步骤，每批256个长度为512的序列，初始学习率为1e-4。
我们能够免费使用一个Google Cloud TPU v3-8（ TensorFlow Research Cloud (TFRC) ），同时利用（ GCP research credits ）。非常感谢这两个Google项目的支持！

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）中提到的LEGAL-BERT-SC模型；该模型是根据下面提到的法律语料库从头开始训练的模型，使用相同语料库训练的句子分隔符分词器创建了一个新的词汇表。

** 由于许多人对LEGAL-BERT-FP模型（依赖于原始BERT-BASE检查点）表示了兴趣，它们已在Archive.org（ https://archive.org/details/legal_bert_fp ）上发布，因为这些模型是次要的，并且可能只对那些有意深入研究Chalkidis等人（2020）中的问题的人有趣。

加载预训练模型

from transformers import AutoTokenizer, AutoModel

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

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')

在下游任务上的评估

请参考文章"LEGAL-BERT：脱离法学院的木偶"。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 开发了能够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：

问题回答系统，涉及数据库、本体、文档集合和网络，特别是生物医学问题回答，
从数据库和本体中生成自然语言，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，
信息提取和观点挖掘，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。

该小组是雅典经济与商业大学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