Download PDFOpen PDF in browser

Multiple Agent Based Entailment System(MABES) for RTE

8 pagesPublished: June 3, 2017

Abstract

Despite growing needs of the legal artificial intelligence (AI), its development is slower than other AI domains because legal expertise is essentially required to develop legal AI systems. Legal knowledge representation on legal expertise needs to be considered to implement legal reasoning AI systems. In this paper, we present a legal reasoning methodology, which utilizes multiple expert knowledge based agents. These agents are designed to solve recognizing textual entailment (RTE) problems with syntactic and interpretative knowledge. The validity of the proposed method is provided through experiments with the COLIEE 2017 data.

Keyphrases: hybrid method for RTE, legal entailment, legal knowledge base, negation rule, recognition textual entailment, RTE, similarity, syntactic analysis

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 23--30

Links:
BibTeX entry
@inproceedings{COLIEE2017:Multiple_Agent_Based_Entailment,
  author    = {Byungtaek Jung and Chiseung Soh and Kihyun Hong and Seungtak Lim and Young-Yik Rhim},
  title     = {Multiple Agent Based Entailment System(MABES) for RTE},
  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},
  pages     = {23--30},
  year      = {2017},
  publisher = {EasyChair},
  bibsource = {EasyChair, http://www.easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/Wj},
  doi       = {10.29007/1gv1}}
Download PDFOpen PDF in browser