Two-Stage Refinement of Transitive Query Translation with English
Disambiguation for Cross-Language Information Retrieval:
A Trial at CLEF 2004
Kazuaki Kishida1 Noriko Kando2 Kuang-Hua Chen3
1 Surugadai University, 698 Azu, Hanno, Saitama 357-8555 Japan
kishida@surugadai.ac.jp
2 National Institute of Informatics (NII), Tokyo 101-8430, Japan
kando@nii.ac.jp
3 National Taiwan University, Taipei 10617, Taiwan
khchen@ntu.edu.tw
Abstract. This paper reports experimental results of cross-language information retrieval (CLIR) from
German to French. The authors are concerned with CLIR in cases where available language resources are
very limited. Thus transitive translation of queries using English as a pivot language was used to search
French document collections for German queries without any direct bilingual dictionary or MT system of
these two languages. The two-stage refinement of query translations that we proposed at the previous CLEF
2003 campaign is again used for enhancing performance of pivot language approach. In particular,
disambiguation of English terms in the middle stage of transitive translation was attempted as a new trial. Our
experiment results show that the two-stage refinement method is able to significantly improve search
performance of bilingual IR using a pivot language, but unfortunately, the English disambiguation has almost
no effect.
1 Introduction
This paper aims at reporting our experiment of cross-language IR (CLIR) from German to French in CLEF 2004.
In the previous CLEF 2003, the authors proposed the “two-stage refinement technique” for enhancing search
performance of pivot language approach in the situation that only limited language resource is available, where
German to Italian search runs were executed using only three resources: (1) a German to English dictionary, (2)
an English to Italian dictionary and (3) target document collection [1]. The target document collection was
employed as a language resource for both translation disambiguation and qu