Dependency-based construction of semantic space models

被引:214
作者
Pado, Sebastian
Lapata, Mirella
机构
[1] Computat Linguist, D-66041 Saarbrucken, Germany
[2] Univ Edinburgh, Sch Informats, Edinburgh EH8 9LW, Midlothian, Scotland
[3] Univ Saarland, D-6600 Saarbrucken, Germany
基金
英国工程与自然科学研究理事会;
关键词
D O I
10.1162/coli.2007.33.2.161
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traditionally, vector-based semantic space models use word co-occurrence counts from large corpora to represent lexical meaning. In this article we present a novel flamework for constructing semantic spaces that takes syntactic relations into account. We introduce a formalization for this class of models, which allows linguistic knowledge to guide the construction process. We evaluate our framework on a range of tasks relevant for cognitive science and natural language processing: semantic priming, synonymy detection, and word sense disambiguation. In all cases, our framework obtains results that are comparable or superior to the state of the art.
引用
收藏
页码:161 / 199
页数:39
相关论文
共 81 条