A DICTIONARY BASED ON CONCEPT COHERENCE

被引：18

作者：

ALTERMAN, R

机构：

[1] Univ of Texas at Austin, Dep of, Computer Science, Austin, TX, USA, Univ of Texas at Austin, Dep of Computer Science, Austin, TX, USA

来源：

ARTIFICIAL INTELLIGENCE | 1985年 / 25卷 / 02期

关键词：

D O I：

10.1016/0004-3702(85)90002-5

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

NEXUS is a computational system which uses a dictionary of 100 to 150 event/state concepts to construct representations of narrative text. Associated with each event/state concept are its deep case relations and their default values. Concepts in the dictionary are related by one of seven event/state concept coherence relations. Relationships between concepts include a list of constraints on the matching of case arguments between the two concepts. NEXUS has been successfully applied to eight paragraph-length samples of text. The resulting discourse representations have been used succesfully to answer questions and compute summaries for these texts.

引用

页码：153 / 186

页数：34