Legal Question Answering System using Neural Attention

11 pages•Published: June 3, 2017

Ayaka Morimoto, Daiki Kubo, Motoki Sato, Hiroyuki Shindo and Yuji Matsumoto

Abstract

This year’s COLIEE has two tasks called phases 1 and 2. The phase 1 needs to find the relevant article given a query t2, and the phase 2 needs to answer whether the given query t2 is yes or no according to Japan civil law articles.
This paper presents our proposals for the phase 2 task. Two methods are presented. The first goes along the standard method taken by many authors, such that the relevant article t1 is selected by the similarity to the query t2 at the requirement (condition) and the effect (conclusion) descriptions of the articles. The second is our new proposal, in which Neural Networks with attention mechanism are applied to all the civil law articles in deciding the truthness of the query t2. This method takes into account all the articles by properly calculating their weighted sum.

Keyphrases: coliee, legal bar exam, question answering, recognizing textual entailment

In: Ken Satoh, Mi-Young Kim, Yoshinobu Kano, Randy Goebel and Tiago Oliveira (editors). COLIEE 2017. 4th Competition on Legal Information Extraction and Entailment, vol 47, pages 79-89.

Links:	https://easychair.org/publications/paper/pqm
	https://doi.org/10.29007/4l2q

BibTeX entry

@inproceedings{COLIEE2017:Legal_Question_Answering_System,
  author    = {Ayaka Morimoto and Daiki Kubo and Motoki Sato and Hiroyuki Shindo and Yuji Matsumoto},
  title     = {Legal Question Answering System using Neural Attention},
  booktitle = {COLIEE 2017. 4th Competition on Legal Information Extraction and Entailment},
  editor    = {Ken Satoh and Mi-Young Kim and Yoshinobu Kano and Randy Goebel and Tiago Oliveira},
  series    = {EPiC Series in Computing},
  volume    = {47},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/pqm},
  doi       = {10.29007/4l2q},
  pages     = {79-89},
  year      = {2017}}

Download PDF Open PDF in browser