Legal Yes/No Question Answering System Using Case-Role Analysis

Lecture Notes in Artificial Intelligence(2017)

引用 5|浏览13
暂无评分
摘要
A central issue of yes/no question answering is the usage of knowledge source given a question. While yes/no question answering has been studied for a long time, legal yes/no question answering largely differs from other domains. The most distinguishing characteristic is that legal issues require precise analysis of roles and relationships of agents named in sentences. We have developed a yes/no question answering system for answering questions about a statute legal domain. Our system uses case-role analysis, in order to find correspondences of roles and relationships between given problem sentences and knowledge source sentences. We applied our system to the JURISIN’s COLIEE (Competition on Legal Information Extraction/Entailment) 2016 task. Our system performance was better than systems of previous task participants and shared first place in current year’s task in Phase Two. This result shows the importance of the points described above, while revealing opportunities to continue further work on improving our system’s accuracy.
更多
查看译文
关键词
COLIEE,Question answering,Legal bar exam,Legal Information Extraction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要