Abstract
This article is prepared for submission to Competition on Legal Information Extraction/Entailment (COLIEE 2022), an international competitive event organized to focus on information processing and retrieval. The proposed method tackles on how to construct an answering system capable of responding Yes/No legal questions, ultimately recognizing entailment between legal queries from past Japanese bar exams and relevant articles of Japan Civil Code (both in Japanese). We first attempted to extract disjunctive union text from each training query and relevant article(s) with corresponding ‘Y/N’ answers as their labels, eventually forming our reference database (training set). Then the same process was repeated on a sample of different queries and relevant articles yet without a ‘Y/N’ label as the input (testing set). Finally, when constructing our model, the similarity ratio between the test disjunctive union and the training disjunctive union by longest common subsequence was calculated as its basis. As a result, this model achieved an accuracy of 0.6055 in Task 4 (rank 3rd as a team, and 7th as a trial). This is an extremely simple and efficient model capable of satisfactory performance.
M. Lin, S.-C. Huang and H.-L. Shao—All authors contributed equally to this work.
H.-L. Shao—Corresponding author
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Rabelo, J., Kim, M.-Y., Goebel, R., Yoshioka, M., Kano, Y., Satoh, K.: A summary of the COLIEE 2019 competition. In: Sakamoto, M., Okazaki, N., Mineshima, K., Satoh, K. (eds.) JSAI-isAI 2019. LNCS (LNAI), vol. 12331, pp. 34–49. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58790-1_3
Rabelo, J., Kim, M.Y., Goebel, R., Yoshioka, M., Kano, Y., Satoh, K.: COLIEE 2020: methods for legal document retrieval and entailment (2020). https://sites.ualberta.ca/~rabelo/COLIEE2021/COLIEE_2020_summary.pdf
Rabelo, J., Goebel, R., Kim, M.Y., Kano, Y., Yoshioka, M., Satoh, K.: Overview and discussion of the competition on legal information extraction/entailment (COLIEE) 2021. Rev. Socionetwork Strat. 16, 111–133 (2022). https://doi.org/10.1007/s12626-022-00105-z
COLIEE organizer. COLIEE-2022 main webpage, Online (2022). https://sites.ualberta.ca/~rabelo/COLIEE2022/
Tohoku NLP Group. Pretrained Japanese BERT models (BERT-base_mecab-ipadic-char-4k_whole-word-mask) (2022). https://github.com/cl-tohoku/bert-japanese
Alinear-corp, albert-japanese. https://github.com/alinear-corp/albert-japanese
Kasper, R.T.: A logical semantics for feature structures. In: 24th Annual Meeting of the Association for Computational Linguistics, pp. 257–266 (1986)
Eiter, T., Gottlob, G., Mannila, H.: Disjunctive datalog. ACM Trans. Database Syst. (TODS) 22(3), 364–418 (1997)
Eiter, T., Gottlob, G.: On the computational cost of disjunctive logic programming: propositional case. Ann. Math. Artif. Intell. 15(3), 289–323 (1995)
Tran, V., Le Nguyen, M., Tojo, S., Satoh, K.: Encoded summarization: summarizing documents into continuous vector space for legal case retrieval. Artif. Intell. Law 28(4), 441–467 (2020). https://doi.org/10.1007/s10506-020-09262-4
Tran, V., Nguyen, M., Satoh, K.: Building legal case retrieval systems with lexical matching and summarization using a pre-trained phrase scoring model. In: ICAIL 2019: Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law June 2019 (2020). https://doi.org/10.1145/3322640.3326740
Anan, Y., Hatano, K., Bannai, H., Takeda, M., Satoh, K.: Polyphonic music classification on symbolic data using dissimilarity functions. In: ISMIR, pp. 229–234 (2012)
Deken, J.G.: Some limit results for longest common subsequences. Discret. Math. 26(1), 17–31 (1979)
Shao, H.-L., Chen, Y.-C., Huang, S.-C.: BERT-based ensemble model for statute law retrieval and legal information entailment. In: Okazaki, N., Yada, K., Satoh, K., Mineshima, K. (eds.) JSAI-isAI 2020. LNCS (LNAI), vol. 12758, pp. 226–239. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-79942-7_15
Bergroth, L., Hakonen, H., Raita, T.: A survey of longest common subsequence algorithms. In: Proceedings Seventh International Symposium on String Processing and Information Retrieval. SPIRE 2000, pp. 39–48. IEEE (2000)
Acknowledgment
Hsuan-lei Shao, “Knowledge Graph of China Studies: Knowledge Extraction, Graph Database, Knowledge Generation” (110-2628-H-003-002-MY4, Ministry of Science and Technology, the MOST), Taiwan.
Sieh-chuen Huang, “A Study on Property Management Regimes in Family and Succession Law in Taiwan” (110-2410-H-002-026-MY3, Ministry of Science and Technology, the MOST), Taiwan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, M., Huang, Sc., Shao, Hl. (2023). Less is Better: Constructing Legal Question Answering System by Weighing Longest Common Subsequence of Disjunctive Union Text. In: Takama, Y., Yada, K., Satoh, K., Arai, S. (eds) New Frontiers in Artificial Intelligence. JSAI-isAI 2022. Lecture Notes in Computer Science(), vol 13859. Springer, Cham. https://doi.org/10.1007/978-3-031-29168-5_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-29168-5_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-29167-8
Online ISBN: 978-3-031-29168-5
eBook Packages: Computer ScienceComputer Science (R0)