论文信息 - Using the Web for Translation Disambiguation: RMIT University at NTCIR-5 Chinese-English CLIR

Using the Web for Translation Disambiguation: RMIT University at NTCIR-5 Chinese-English CLIR

RMIT University participated in the Chinese– English NTCIR-5 CLIR task. In previous work, researchers have relied on the test collection corpus to perform translation disambiguation in CLIR. In a production system, one would not be able to use a constrained test collection for disambiguation. Therefore we are interested to see how well our techniques perform when the web is used to provide context for disambiguation. Our experimental results show that when using the web, it is possible to achieve effectiveness comparable to that obtained with a test collection.

Ying Zhang | Phil Vines

[1] Mirna Adriani. Using Statistical Term Similarity for Sense Disambiguation in Cross-Language Information Retrieval , 2004, Information Retrieval.

[2] Richard M. Schwartz,et al. A hidden Markov model information retrieval system , 1999, SIGIR '99.

[3] W. Bruce Croft,et al. Resolving ambiguity for cross-language retrieval , 1998, SIGIR '98.

[4] Marcello Federico,et al. Statistical cross-language information retrieval using n-best query translations , 2002, SIGIR '02.

[5] Ying Zhang,et al. RMIT Chinese-English CLIR at NTCIR-4 , 2004, NTCIR.

[6] Hermann Ney,et al. On structuring probabilistic dependences in stochastic language modelling , 1994, Comput. Speech Lang..

[7] Jianfeng Gao,et al. Resolving query translation ambiguity using a decaying co-occurrence model and syntactic dependence relations , 2002, SIGIR '02.

[8] Shui-Lung Chuang,et al. Subject categorization of query terms for exploring Web users' search interests , 2002, J. Assoc. Inf. Sci. Technol..

[9] Ophir Frieder,et al. Effective arabic-english cross-language information retrieval via machine-readable dictionaries and machine translation , 2001, CIKM '01.

[10] Ying Zhang,et al. Using the web for automated translation extraction in cross-language information retrieval , 2004, SIGIR '04.