COLIEE 2020: Legal Information Retrieval and Entailment with Legal Embeddings and Boosting

被引:3
作者
Alberts, Houda [1 ]
Ipek, Akin [1 ]
Lucas, Roderick [1 ]
Wozny, Phillip [1 ]
机构
[1] Deloitte NL, Tax I Team, Amsterdam, Netherlands
来源
NEW FRONTIERS IN ARTIFICIAL INTELLIGENCE, JSAI-ISAI 2020 | 2021年 / 12758卷
关键词
Legal information retrieval; Textual entailment; Classification; Natural language inference; Ranking; Legal embeddings; BERT; Boosting; LAW;
D O I
10.1007/978-3-030-79942-7_14
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we investigate three different methods for several legal document retrieval and entailment tasks; namely, new low complexity pre-trained embeddings, specifically trained on documents in the legal domain, transformer models and boosting algorithms. Task 1, a case law retrieval task, utilized a pairwise CatBoost resulting in an F1 score of .04. Task 2, a case law entailment task, utilized a combination of BM25+, embeddings and natural language inference (NLI) features winning third place with an F1 of 0.6180. Task 3, a statutory information retrieval task, utilized the aforementioned pre-trained embeddings in combination with TF-IDF features resulting in an F2 score of 0.4546. Lastly, task 4, a statutory entailment task, utilized BERT embeddings with XGBoost and achieved an accuracy of 0.5357. Notably, our Task 2 submission was the third best in the competition. Our findings illustrate that using legal embeddings and auxiliary linguistic features, such as NLI, show the most promise for future improvements.
引用
收藏
页码:211 / 225
页数:15
相关论文
共 35 条
[1]  
Androutsopoulos I., 2019, ARXIV PREPRINT ARXIV
[2]  
Benjamins V.R., 2005, LAW SEMANTIC WEB LEG, V3369, DOI [10.1007/b106624, DOI 10.1007/B106624]
[3]  
Bojanowski P., 2017, T ASSOC COMPUT LING, V5, P135, DOI [10.1162/tacl_a_00051, DOI 10.1162/TACLA00051]
[4]  
Chen T., 2015, R package version 0.4-2, V1, P1, DOI DOI 10.1145/2939672.2939785
[5]  
Clement J., 2019, WORLDWIDE DESKTOP MA
[6]   Industry Watch Law and Word Order : NLP in Legal Tech [J].
Dale, Robert .
NATURAL LANGUAGE ENGINEERING, 2019, 25 (01) :211-217
[7]  
Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171
[8]  
Dorogush AV., 2018, ARXIV, DOI DOI 10.3390/RS13142805
[9]  
Gain B., 2019, IITP COLIEE ICAIL 20
[10]  
Holzenberger N., 2020, P 2020 NAT LEG LANG