Answering contextual questions based on the cohesion with knowledge

COMPUTER PROCESSING OF ORIENTAL LANGUAGES, PROCEEDINGS: BEYOND THE ORIENT: THE RESEARCH CHALLENGES AHEAD(2012)

引用 6|浏览0
暂无评分
摘要
In this paper, we propose a Japanese question-answering (QA) system to answer contextual questions using a Japanese non-contextual QA system. The contextual questions usually contain reference expressions to refer to previous questions and their answers. We address the reference resolution in contextual questions by finding the interpretation of references so as to maximize the cohesion with knowledge. We utilize the appropriateness of the answer candidate obtained from the non-contextual QA system as the degree of the cohesion. The experimental results show that the proposed method is effective to disambiguate the interpretation of contextual questions.
更多
查看译文
关键词
japanese question-answering,previous question,japanese non-contextual qa system,non-contextual qa system,reference resolution,answer candidate,contextual question,reference expression,question answering system
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