A maximum coherence model for dictionary-based crosslanguage information retrieval

A maximum coherence model for dictionary-based crosslanguage information retrieval (2005)

Cached

Download Links

by Yi Liu , Joyce Y. Chai

Venue:	In SIGIR ’05: Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Citations:	4 - 0 self

Versions

Version History

Metadata Version 0

Datum	Value	Source
TITLE	A Maximum Coherence Model for Dictionary-based Cross-language Information Retrieval ABSTRACT	SVM HeaderParse 0.2
AUTHOR NAME	Yi Liu	SVM HeaderParse 0.2
AUTHOR AFFIL	; Dept. of Computer Science; and Engineering; Michigan State University; Categories and Subject Descriptors; Search and Retrieval—Retrieval Models; Dept. of Computer	SVM HeaderParse 0.2
AUTHOR ADDR	; East Lansing, MI 48824; East Lansing, MI 48824; 536	SVM HeaderParse 0.2
AUTHOR NAME	Joyce Y. Chai	SVM HeaderParse 0.2
AUTHOR AFFIL	Dept...	SVM HeaderParse 0.2
ABSTRACT	One key to cross-language information retrieval is how to efficiently resolve the translation ambiguity of queries given their short length. This problem is even more challenging when only bilingual dictionaries are available, which is the focus of this paper. In the previous research of crosslanguage information retrieval using bilingual dictionaries, the word co-occurrence statistics is used to determine the most likely translations of queries. In this paper, we propose a novel statistical model, named “maximum coherence model”, which estimates the translation probabilities of query words that are consistent with the word co-occurrence statistics. Unlike the previous work, where a binary decision is made for the selection of translations, the new model maintains the uncertainty in translating query words when their sense ambiguity is difficult to resolve. Furthermore, this new model is able to estimate translations of multiple query words simultaneously. This is in contrast to many previous approaches where translations of individual query words are determined independently. Empirical studies with TREC datasets have shown that the maximum coherence model achieves a relative 10 %- 40 % improvement in cross-language information retrieval, comparing to other approaches that also use word co-occurrence statistics for sense disambiguation.	SVM HeaderParse 0.2
CITATIONS	21 found	ParsCit 1.0