Abstract
This paper presents a study on exploiting reference information to build a question answering system restricted to the legal domain. Most previous research focuses on answering legal questions whose answers can be found in one document (The term ‘documents’ corresponds to articles, paragraphs, items, or sub-items according to the naming rules used in the legal domain.) without using reference information. However, there are many legal questions whose answers could not be found without linking information from multiple documents. This connection is represented by explicit or implicit references. To the best of our knowledge, this type of questions is not adequately considered in previous work. To cope with them, we propose a novel approach which allow us to exploit the reference information among legal documents to find answers. This approach also uses requisite-effectuation structures of legal sentences and some effective similarity measures to support finding correct answers without training data. The experimental results showed that the proposed method is quite effective and outperform a traditional QA method, which does not use reference information.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
- 3.
The reason why they call them high-level is that each requisite part or effectuation part consists of several logical parts.
- 4.
To understand more about four cases of legal sentences and their logical parts, please check the paper of Bach et al. [2].
- 5.
We can use these characteristics for a QA system as shown in Tomura, K., A study on a question answering system for laws, Master thesis, JAIST, 2013. The system answers to a question based on only one document.
- 6.
- 7.
- 8.
We used synonym list extracted from Japanese WordNet Copyright 2009, 2012 by National Institute of Information and Communications Technology (NiCT).
- 9.
The paragraph which contains the reference referring to the referenced paragraph.
- 10.
This tool got the accuracy of \(\sim \) 90 %.
- 11.
We did not count the number of definition in parentheses and only count paragraph main sentences.
References
Anne, R.D., Yilmazel, O., Liddy, E.D.: Evaluation of restricted domain question-answering systems. In: Proceedings of Workshop on Question Answering in Restricted Domains, ACL, pp. 2–7 (2004)
Bach, N.X., Minh, N.L., Oanh, T.T., Shimazu, A.: A two-phase framework for learning logical structures of paragraphs in legal articles. J. ACM TALIP 12((1, article no 3)), 1–32 (2013)
Bach, N.X., Minh, N.L., Shimazu, A.: Recognition of requisite part and effectuation part in law sentences. In: Proceedings of ICCPOL, pp. 29–34 (2010)
Bach, N.X., Minh, N.L., Shimazu, A.: Rre task: The task of recognition of requisite part and effectuation part in law sentences. J. IJCPOL 23(2), 109–130 (2010)
Doan-Nguyen, H., Kosseim, L.: The problem of precision in restricted-domain question-answering. In: Proceedings of Workshop on Question Answering in Restricted Domains, ACL, pp. 8–15 (2004)
Jurafsky, D., Martin, J.H.: Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition. Prentice Hall Series in Artificial Intelligence, 2nd edn. Prentice Hall, Upper Saddle River (2009)
Ciaramita, M., Surdeanu, M., Zaragoza, H.: Learning to rank answers on large online qa collections. In: Proceedings of the ACL-HLT, pp. 719–727 (2008)
Manning, C.D., Raghana, P., Schutze, H.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)
Monroy, A., Calvo, H., Gelbukh, A.: NLP for shallow question answering of legal documents using graphs. In: Gelbukh, A. (ed.) CICLing 2009. LNCS, vol. 5449, pp. 498–508. Springer, Heidelberg (2009)
Paik, J.H.: A novel tf-idf weighting scheme for effective ranking. In: Proceedings of ACM SIGIR, pp. 343–352 (2013)
Paltoglo, G., Thelwall, M.: A study of information retrieval weighting schemes for sentiment analysis. In: Proceedings of ACL, pp. 1386–1395 (2010)
Paulo, Q., Rodrigues, I.P.: A question-answering system for portuguese juridical documents. In: Proceedings of the ICAIL, pp. 256–257 (2005)
Peñas, A.: Overview of ResPubliQA 2009: question answering evaluation over european legislation. In: Peters, C., Di Nunzio, G.M., Kurimo, M., Mandl, T., Mostefa, D., Peñas, A., Roda, G. (eds.) CLEF 2009 Workshop, Part I. LNCS, vol. 6241, pp. 174–196. Springer, Heidelberg (2010)
Robertson, S., Walker, S.: On relevance weights with little relevance information. In: Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 16–24 (1997)
Robertson, S., Zaragoza, S.: The probabilistic relevance framework: Bm25 and beyond. J. Found. Trends Inf. Retrieval 3, 333–389 (2009)
Takano, K., Nakamura, M., Oyama, Y., Shimazu, A.: Semantic analysis of paragraphs consisting of multiple sentences - towards development of a logical formulation system. In: Proceedings of JURIX, pp. 117–126 (2010)
Tanaka, K., Kawazoe, I., Narita, H.: Standard structure of legal provisions for the legal knowledge processing by natural language. In Research report on Natural Language Processing, IPSJ, pp. 79–86 (1993) (in Japanese)
Tomura, K.: Study on question answering system for laws. Technical report, School of Information Science, Japan Advanced Institute of Science and Technology (JAIST) (2013)
Tran, O.T., Ngo, B.X., Le Nguyen, M., Shimazu, A.: Reference resolution in legal texts. In: Proceedings of ICAIL, pp. 101–110 (2013)
Zhang, W., Yoshida, T., Tang, X.: A comparative study of TF*IDF, LSI and multi-words for text classification. Expert Syst. Appl. Int. J. 38, 2758–2765 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Tran, O.T., Ngo, B.X., Le Nguyen, M., Shimazu, A. (2014). Answering Legal Questions by Mining Reference Information. In: Nakano, Y., Satoh, K., Bekki, D. (eds) New Frontiers in Artificial Intelligence. JSAI-isAI 2013. Lecture Notes in Computer Science(), vol 8417. Springer, Cham. https://doi.org/10.1007/978-3-319-10061-6_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-10061-6_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10060-9
Online ISBN: 978-3-319-10061-6
eBook Packages: Computer ScienceComputer Science (R0)