{"type":"ScholarlyArticle","title":"BERT-PLI: Modeling Paragraph-Level Interactions for Legal Case Retrieval","authors":[{"name":"Yunqiu Shao","slug":"yunqiu-shao","given":"Yunqiu","family":"Shao","affiliation":"BNRist , DCST , Tsinghua University , Beijing , China"},{"name":"Jiaxin Mao","slug":"jiaxin-mao","given":"Jiaxin","family":"Mao","affiliation":"BNRist , DCST , Tsinghua University , Beijing , China"},{"name":"Yiqun Liu","slug":"yiqun-liu","given":"Yiqun","family":"Liu","affiliation":"BNRist , DCST , Tsinghua University , Beijing , China"},{"name":"Weizhi Ma","slug":"weizhi-ma","given":"Weizhi","family":"Ma","affiliation":"BNRist , DCST , Tsinghua University , Beijing , China"},{"name":"Ken Satoh","slug":"ken-satoh","given":"Ken","family":"Satoh","affiliation":"National Institute of Informatics , Tokyo , Japan"},{"name":"Min Zhang","slug":"min-zhang","given":"Min","family":"Zhang","affiliation":"BNRist , DCST , Tsinghua University , Beijing , China"},{"name":"Shaoping Ma","slug":"shaoping-ma","given":"Shaoping","family":"Ma","affiliation":"BNRist , DCST , Tsinghua University , Beijing , China"}],"abstract":"Legal case retrieval is a specialized IR task that involves retrieving supporting cases given a query case. Compared with traditional ad-hoc text retrieval, the legal case retrieval task is more challenging since the query case is much longer and more complex than common keyword queries. Besides that, the definition of relevance between a query case and a supporting case is beyond general topical relevance and it is therefore difficult to construct a large-scale case retrieval dataset, especially one with accurate relevance judgments. To address these challenges, we propose BERT-PLI, a novel model that utilizes BERT to capture the semantic relationships at the paragraph-level and then infers the relevance between two cases by aggregating paragraph-level interactions. We fine-tune the BERT model with a relatively small-scale case law entailment dataset to adapt it to the legal scenario and employ a cascade framework to reduce the computational cost. We conduct extensive experiments on the benchmark of the relevant case retrieval task in COLIEE 2019. Experimental results demonstrate that our proposed method outperforms existing solutions.","doi":"10.24963/ijcai.2020/484","url":"https://ijcai.org/proceedings/2020/484","pdf":"https://ijcai.org/proceedings/2020/0484.pdf","markdown":"https://ijcai.org/proceedings/2020/484.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/484","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Multidisciplinary Topics and Applications","track":"Main track","number":484,"pages":{"first":3501,"last":3507},"keywords":["Multidisciplinary Topics and Applications: Information Retrieval","Natural Language Processing: Information Retrieval","Machine Learning Applications: Other"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25749/file_25749.m3u8","length_sec":751,"provider":"hls"}],"references":[{"position":1,"raw":"[Bench-Capon et al., 2012] Trevor Bench-Capon, Michał Araszkiewicz, Kevin Ashley, Katie Atkinson, Floris Bex, Filipe Borges, Daniele Bourcier, Paul Bourgine, Jack G Conrad, Enrico Francesconi, et al. A history of AI and law in 50 papers: 25 years of the international conference on AI and law. AI & Law, 20(3):215-319, 2012.","title":"A history of AI and law in 50 papers: 25 years of the international conference on AI and law","authors":"Trevor Bench-Capon, Michał Araszkiewicz, Kevin Ashley, Katie Atkinson, Floris Bex, Filipe Borges, Daniele Bourcier, Paul Bourgine, G Jack, Enrico Conrad, Francesconi","year":"2012","venue":"AI & Law","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bhattacharya et al., 2019] Paheli Bhattacharya, Kripa- bandhu Ghosh, Saptarshi Ghosh, Arindam Pal, Parth Mehta, Arnab Bhattacharya, and Prasenjit Majumder. Overview of the FIRE 2019 AILA track: Artificial intelligence for legal assistance. FIRE'19, pages 12-15, 2019.","title":"Overview of the FIRE 2019 AILA track: Artificial intelligence for legal assistance. FIRE'19","authors":"Bhattacharya","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dai and Callan, 2019] Zhuyun Dai and Jamie Callan. Deeper text understanding for IR with contextual neural language modeling. arXiv:1905.09217, 2019.","title":"Deeper text understanding for IR with contextual neural language modeling","authors":"Callan Dai, Zhuyun Dai, Jamie Callan","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Devlin et al., 2018] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understand- ing. arXiv:1810.04805, 2018.","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Guo et al., 2019] Jiafeng Guo, Yixing Fan, Xiang Ji, and Xueqi Cheng. MatchZoo: A learning, practicing, and de- veloping system for neural text matching. In SIGIR'19, pages 1297-1300, New York, NY, USA, 2019. ACM.","title":"MatchZoo: A learning, practicing, and developing system for neural text matching","authors":"Guo","year":"2019","venue":"SIGIR'19","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hu et al., 2014] Baotian Hu, Zhengdong Lu, Hang Li, and Qingcai Chen. Convolutional neural network architectures for matching natural language sentences. In NeurlPS'14, pages 2042-2050, 2014.","title":"Convolutional neural network architectures for matching natural language sentences","authors":"Baotian Hu, Zhengdong Lu, Hang Li, Qingcai Chen","year":"2014","venue":"NeurlPS'","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Lin, 2004] Chin-Yew Lin. ROUGE: A package for auto- matic evaluation of summaries. In Text Summarization Branches Out, pages 74-81, 2004.","title":"ROUGE: A package for automatic evaluation of summaries","authors":"Chin-Yew Lin","year":"2004","venue":"Text Summarization Branches Out","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Liu and others, 2009] Tie-Yan Liu et al. Learning to rank for information retrieval. FnTIR, 3(3):225-331, 2009.","title":"Learning to rank for information retrieval","authors":"Others ; Tie-Yan Liu, Liu","year":"2009","venue":"FnTIR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Maxwell and Schafer, 2008] K Tamsin Maxwell and Burkhard Schafer. Concept and context in legal informa- tion retrieval. In JURIX, pages 63-72, 2008.","title":"Concept and context in legal information retrieval","authors":"Schafer ; K Tamsin Maxwell, Burkhard Maxwell, Schafer","year":"2008","venue":"JURIX","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Mihalcea and Tarau, 2004] Rada Mihalcea and Paul Tarau. TextRank: Bringing order into text. In EMNLP'04, pages 404-411, 2004.","title":"TextRank: Bringing order into text","authors":"Tarau Mihalcea, Rada Mihalcea, Paul Tarau","year":"2004","venue":"EMNLP'04","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Monroy et al., 2013] Alfredo López Monroy, Hiram Calvo, Alexander Gelbukh, and Georgina García Pacheco. Link analysis for representing and retrieving legal information. In CICLing'13, pages 380-393. Springer, 2013.","title":"Link analysis for representing and retrieving legal information","authors":"Alfredo López Monroy, Hiram Calvo, Alexander Gelbukh, Georgina García Pacheco","year":"2013","venue":"CICLing'13","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Oard et al., 2013] Douglas W Oard, William Webber, et al. Information retrieval for e-discovery. FnTIR, 7(2-3):99- 237, 2013.","title":"Information retrieval for e-discovery","authors":"William Douglas W Oard, Webber","year":"2013","venue":"FnTIR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Palangi et al., 2016] Hamid Palangi, Li Deng, Yelong Shen, Jianfeng Gao, Xiaodong He, Jianshu Chen, Xinying Song, and Rabab Ward. Deep sentence embedding using long short-term memory networks: Analysis and application to information retrieval. TASLP'16, 24(4):694-707, 2016.","title":"Deep sentence embedding using long short-term memory networks: Analysis and application to information retrieval","authors":"Hamid Palangi, Li Deng, Yelong Shen, Jianfeng Gao, Xiaodong He, Jianshu Chen, Xinying Song, Rabab Ward","year":"2016","venue":"TASLP'","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Pang et al., 2016] Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Shengxian Wan, and Xueqi Cheng. Text matching as image recognition. In AAAI'16, 2016.","title":"Text matching as image recognition","authors":"Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Shengxian Wan, Xueqi Cheng","year":"2016","venue":"AAAI'16","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Rabelo et al., 2019] Juliano Rabelo, Mi-Young Kim, Randy Goebel, Masaharu Yoshioka, Yoshinobu Kano, and Ken Satoh. COLIEE 2019 overview. In COLIEE'19, pages 1-9, 2019.","title":"COLIEE 2019 overview","authors":"Juliano Rabelo, Mi-Young Kim, Randy Goebel, Masaharu Yoshioka, Yoshinobu Kano, Ken Satoh","year":"2019","venue":"COLIEE'19","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Robertson and Walker, 1994] Stephen E Robertson and Steve Walker. Some simple effective approximations to the 2-poisson model for probabilistic weighted retrieval. In SIGIR'94, pages 232-241. Springer, 1994.","title":"Some simple effective approximations to the 2-poisson model for probabilistic weighted retrieval","authors":"E Stephen, Steve Robertson, Walker","year":"1994","venue":"SIGIR'94","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Rossi and Kanoulas, 2019] Juline Rossi and Evangelos Kanoulas. Legal information retrieval with generalized language models. In COLIEE'19, pages 16-19, 2019.","title":"Legal information retrieval with generalized language models","authors":"Juline Rossi, Evangelos Kanoulas","year":"2019","venue":"COLIEE'19","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Salton and Buckley, 1988] Gerard Salton and Christopher Buckley. Term-weighting approaches in automatic text re- trieval. IP&M, 24(5):513-523, 1988.","title":"Term-weighting approaches in automatic text retrieval","authors":"Buckley Salton, Gerard Salton, Christopher Buckley","year":"1988","venue":"IP&M","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Saravanan et al., 2009] M Saravanan, Balaraman Ravin- dran, and S Raman. Improving legal information retrieval using an ontological framework. AI & Law, 17(2):101- 124, 2009.","title":"Improving legal information retrieval using an ontological framework","authors":"Balaraman Saravanan, Ravindran, Raman","year":"2009","venue":"AI & Law","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shen et al., 2014] Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, and Grégoire Mesnil. A latent semantic model with convolutional-pooling structure for informa- tion retrieval. In CIKM'14, pages 101-110. ACM, 2014.","title":"A latent semantic model with convolutional-pooling structure for information retrieval","authors":"Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, Grégoire Mesnil","year":"2014","venue":"CIKM'14","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Song and Croft, 1999] Fei Song and W Bruce Croft. A general language model for information retrieval. In CIKM'99, pages 316-321. ACM, 1999.","title":"A general language model for information retrieval","authors":"Fei Song, Bruce Croft","year":"1999","venue":"CIKM'99","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tran et al., 2019] Vu Tran, Minh Le Nguyen, and Ken Satoh. Building legal case retrieval systems with lexical matching and summarization using a pre-trained phrase scoring model. In ICAIL'19, pages 275-282, 2019.","title":"Building legal case retrieval systems with lexical matching and summarization using a pre-trained phrase scoring model","authors":"Minh Le Vu Tran, Ken Nguyen, Satoh","year":"2019","venue":"ICAIL'19","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Turtle, 1995] Howard Turtle. Text retrieval in the legal world. AI & Law, 3(1-2):5-54, 1995.","title":"Howard Turtle. Text retrieval in the legal world","authors":"Turtle","year":"1995","venue":"AI & Law","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Van Opijnen and Santos, 2017] Marc Van Opijnen and Cristiana Santos. On the concept of relevance in legal information retrieval. AI & Law, 25(1):65-87, 2017.","title":"On the concept of relevance in legal information retrieval","authors":"Santos ; Van Opijnen, Marc Van Opijnen, Cristiana Santos","year":"2017","venue":"AI & Law","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wan et al., 2016] Shengxian Wan, Yanyan Lan, Jun Xu, Ji- afeng Guo, Liang Pang, and Xueqi Cheng. Match-SRNN: Modeling the recursive matching structure with spatial RNN. arXiv:1604.04378, 2016.","title":"Match-SRNN: Modeling the recursive matching structure with spatial RNN","authors":"Shengxian Wan, Yanyan Lan, Jun Xu, Jiafeng Guo, Liang Pang, Xueqi Cheng","year":"2016","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2016/415"},{"position":26,"raw":"[Xu et al., 2018] Jun Xu, Xiangnan He, and Hang Li. Deep learning for matching in search and recommendation. In SIGIR'18, pages 1365-1368. ACM, 2018.","title":"Deep learning for matching in search and recommendation","authors":"Xu","year":"2018","venue":"SIGIR'18","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yilmaz et al., 2019] Zeynep Akkalyoncu Yilmaz, Wei Yang, Haotian Zhang, and Jimmy Lin. Cross-domain modeling of sentence-level evidence for document retrieval. In EMNLP-IJCNLP'19, pages 3481-3487, 2019.","title":"Cross-domain modeling of sentence-level evidence for document retrieval","authors":"Akkalyoncu Zeynep, Wei Yilmaz, Haotian Yang, Jimmy Zhang, Lin","year":"2019","venue":"EMNLP-IJCNLP'19","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zeng et al., 2005] Yiming Zeng, Ruili Wang, John Zeleznikow, and Elizabeth Kemp. Knowledge represen- tation for the intelligent legal case retrieval. In KES'05, pages 339-345. Springer, 2005.","title":"Knowledge representation for the intelligent legal case retrieval","authors":"Yiming Zeng, Ruili Wang, John Zeleznikow, Elizabeth Kemp","year":"2005","venue":"KES'05","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}