Resolving query translation ambiguity using a decaying co-occurrence model and syntactic dependence relations

  • Authors:

  • Jianfeng Gao;Ming Zhou;Jian-Yun Nie;Hongzhao He;Weijun Chen

  • Affiliations:

  • Microsoft Research, Asia;Microsoft Research, Asia;Université de Montréal;Tianjin University, China;Tianjin University, China

  • Venue:
  • SIGIR '02 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

Bilingual dictionaries have been commonly used for query translation in cross-language information retrieval (CLIR). However, we are faced with the problem of translation selection. Several recent studies suggested the utilization of term co-occurrences in this selection. This paper presents two extensions to improve them. First, we extend the basic co-occurrence model by adding a decaying factor that decreases the mutual information when the distance between the terms increases. Second, we incorporate a triple translation model, in which syntactic dependence relations (represented as triples) are integrated. Our evaluation on translation accuracy shows that translating triples as units is more precise than a word-by-word translation. Our CLIR experiments show that the addition of the decaying factor leads to substantial improvements of the basic co-occurrence model; and the triple translation model brings further improvements.