A STUDY OF TEXTUAL ENTAILMENT

被引：8
作者：
Rus, Vasile [1 ,2 ]
McCarthy, Philip M. [1 ,3 ]
McNamara, Danielle S. [1 ,4 ]
Graesser, Arthur C. [1 ,4 ]
机构：
[1] Univ Memphis, Inst Intelligent Syst, Memphis, TN 38152 USA
[2] Univ Memphis, Dept Comp Sci, Memphis, TN 38152 USA
[3] Univ Memphis, Dept English, Memphis, TN 38152 USA
[4] Univ Memphis, Dept Psychol, Memphis, TN 38152 USA
来源：
INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS | 2008年 / 17卷 / 04期
基金：
美国国家科学基金会;
关键词：
Textual entailment; syntactic dependencies; natural language processing; graph subsumption;
D O I：
10.1142/S0218213008004096
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper we study a graph-based approach to the task of Recognizing Textual Entailment between a Text and a Hypothesis. The approach takes into account the full lexico-syntactic context of both the Text and Hypothesis and is based on the concept of subsumption. It starts with mapping the Text and Hypothesis on to graph structures that have nodes representing concepts and edges representing lexico-syntactic relations among concepts. An entailment decision is then made on the basis of a subsumption score between the Text-graph and Hypothesis-graph. The results obtained from a standard entailment test data set were promising. The impact of synonymy on entailment is quantified and discussed. An important advantage to a solution like ours is its ability to be customized to obtain high-confidence results.
引用
收藏
页码：659 / 685
页数：27
相关论文
共 45 条
  • [1] ANDREEVSKAIA A, 2005, P REC TEXT ENT CHALL
  • [2] BRAZ RD, 2005, P REC TEXT ENT CHALL
  • [3] Chapman WW, 2001, J AM MED INFORM ASSN, P105
  • [4] CHARNIAK E, 1997, P 14 NAT C ART INT
  • [5] Charniak Eugene, 2000, P N AM CHAPT ASS COM
  • [6] SPREADING ACTIVATION THEORY OF SEMANTIC PROCESSING
    COLLINS, AM
    LOFTUS, EF
    [J]. PSYCHOLOGICAL REVIEW, 1975, 82 (06) : 407 - 428
  • [7] CORLEY C, 2005, P ACL 2005 WORKSH EM
  • [8] Cristianini N., 2000, Intelligent Data Analysis: An Introduction
  • [9] DAGAN I, 2005, P REC TEXT ENT CHALL
  • [10] DAGAN I, 2004, RECOGNIZING TEXTUAL
12345