Artificial Intelligence and Law 23 (4):315-344 (2015)
AbstractThis article addresses the problem of automatically extracting legal indices which express the important contents of legal documents. Legal indices are not limited to single-word keywords and compound-word keywords, they are also clause keywords. We approach index extraction using structural information of Japanese sentences, i.e. chunks and clauses. Based on the assumption that legal indices are composed of important tokens from the documents, extracting legal indices is treated as a problem of collecting chunks and clauses that contain as many important tokens as possible. Each token is assigned a weight which is a statistical score, e.g. TF–IDF and Okapi BM25, to indicate its importance. The importance of a chunk or clause is determined based on the average weight of tokens included in that chunk or clause. Then, highly weighted chunks and clauses are recognized as the indices for legal documents. The experimental results on Japanese National Pension Act data show that our proposed method achieves better performance than TextRank, the most popular unsupervised method in extracting single-word and compound-word keywords. In addition, this approach is also applicable to extract clause keywords with high performance.
Similar books and articles
Automated reference resolution in legal texts.Oanh Thi Tran, Bach Xuan Ngo, Minh Le Nguyen & Akira Shimazu - 2014 - Artificial Intelligence and Law 22 (1):29-60.
The rules of law in the reform of legal education: Teaching the legal mind in japanese law schools.James R. Maxeiner - unknown
East and West Legal Philosophies in Japan : Japanese Association for Legal and Social Philosophy, Annual Conference, 13th-15th November, 1986. [REVIEW]Mitsukuni Japanese Association for Legal and Social Philosophy & Yazaki - 1987
TULSI: an NLP system for extracting legal modificatory provisions. [REVIEW]Leonardo Lesmo, Alessandro Mazzei, Monica Palmirani & Daniele P. Radicioni - 2013 - Artificial Intelligence and Law 21 (2):139-172.
Pension System in Japan: Issues for Reform.Audrius Bitinas - 2012 - Jurisprudencija: Mokslo darbu žurnalas 19 (1):269-292.
Bactrian Documents from Northern Afghanistan, I: Legal and Economic Documents by Nicholas Sims-Williams. [REVIEW]Prods Skjaerve - 2005 - Journal of the American Oriental Society 125 (2):311-316.
Sourcebook for Modern Japanese Philosophy: Selected Documents.David A. Dilworth, V. H. Viglielmo & Agustín Jacinto Zavala (eds.) - 1998 - Greenwood Press.
American law schools as a model for japanese legal education? A preliminary question from a comparative perspective.James R. Maxeiner - unknown
Legal English – Changing Perspective.Maja Stanojevic - 2011 - Facta Universitatis, Series: Linguistics and Literature 9 (1):65-75.
The voting power approach : a theory of measurement. A response to Max Albert.Christian List - 2003 - European Union Politics 4 (4):487-497.
Why Patients Sue Doctors: The Japanese Experience.Eric A. Feldman - 2009 - Journal of Law, Medicine and Ethics 37 (4):792-799.
Integrated access to legal literature through automated semantic classification.E. Francesconi & G. Peruginelli - 2009 - Artificial Intelligence and Law 17 (1):31-49.
Added to PP
Historical graph of downloads
Citations of this work
A sequence labeling model for catchphrase identification from legal case documents.Arpan Mandal, Kripabandhu Ghosh, Saptarshi Ghosh & Sekhar Mandal - 2022 - Artificial Intelligence and Law 30 (3):325-358.
On computable numbers with an application to the AlanTuringproblem.C. F. Huws & J. C. Finnis - 2017 - Artificial Intelligence and Law 25 (2):181-203.
Using attention methods to predict judicial outcomes.Vithor Gomes Ferreira Bertalan & Evandro Eduardo Seron Ruiz - forthcoming - Artificial Intelligence and Law:1-29.
References found in this work
Foundations of Statistical Natural Language Processing.Christopher Manning & Hinrich Schutze - 1999 - MIT Press.
Improving legal information retrieval using an ontological framework.M. Saravanan, B. Ravindran & S. Raman - 2009 - Artificial Intelligence and Law 17 (2):101-124.