Natural Language Search Based on Subdividing Objects of Search Using Predicate Argument Structure Analysis

IR (HANDLE) Web Site 19 References Open Access

Bibliographic Information

Other Title
  • 述語項構造解析による検索対象細分化を用いた自然文検索
  • ジュツゴコウ コウゾウ カイセキ ニ ヨル ケンサク タイショウ サイブンカ オ モチイタ シゼンブン ケンサク

Search this article

Description

In this paper we describe our system for retrieving texts using predicate argument structure analysis for queries in natural language. A dependency relation included in a query decides a word score, which is retrieved by defining "retrieval subject" that further becomes the main clue for retrieving sentences using a word classified by predicate argument structure analysis tool SynCha as "-ga case". As a result, the problem of biased word score can be corrected. In this research we target judicial precedents of traffic accidents and use "Oshiete! goo" online QA community entries for experiments.

Journal

References(19)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top