Caption vs. Query Translation for Cross-Language Image Retrieval

For many cross-language retrieval tasks, the predominant approach is to translate the query into the language of the document collection (target language). This often gives results as good as, if not better, than translating the document collection into the query language (source language). In this paper, we evaluate query versus document translation for the ImageCLEF 2004 bilingual ad hoc retrieval task. Image retrieval is achieved through matching textual queries to associated image captions for the following languages: French, German, Spanish and Italian using commercially and publicly available resources. On average, we find query translation to outperform document translation (77% of English MAP compared to 65% respectively) but this varies widely across language and query. Combining document and query translation we achieve an average MAP of 85% of English.

[1]  Carol Peters,et al.  European research letter: Cross-language system evaluation: The CLEF campaigns , 2001, J. Assoc. Inf. Sci. Technol..

[2]  Mark Sanderson,et al.  Assessing Translation Quality for Cross Language Image Retrieval , 2003, CLEF.

[3]  Carol Peters,et al.  Multilingual Information Access for Text, Speech and Images, 5th Workshop of the Cross-Language Evaluation Forum, CLEF 2004, Bath, UK, September 15-17, 2004, Revised Selected Papers , 2005, CLEF.

[4]  Sharon Flank.  Cross-Language Multimedia Information Retrieval , 2000, ANLP.

[5]  Mark Sanderson,et al.  The CLEF Cross Language Image Retrieval Track (ImageCLEF) 2004 , 2004, CLEF.

[6]  Mark Sanderson,et al.  The CLEF 2004 Cross-Language Image Retrieval Track , 2004, CLEF.

[7]  Mark Sanderson,et al.  User experiments with the Eurovision cross-language image retrieval system , 2006, J. Assoc. Inf. Sci. Technol..

[8]  Harold L. Somers,et al.  An introduction to machine translation , 1992 .

[9]  Douglas W. Oard,et al.  A comparative study of query and document translation for cross-language information retrieval , 1998, AMTA.

[10]  Tetsuya Ishikawa,et al.  Applying Machine Translation to Two-Stage Cross-Language Information , 2000, AMTA.

[11]  John D. Lafferty,et al.  A study of smoothing methods for language models applied to Ad Hoc information retrieval , 2001, SIGIR '01.

[12]  J. Scott McCarley.  Should we Translate the Documents or the Queries in Cross-language Information Retrieval? , 1999, ACL.

[13]  Gregory Grefenstette,et al.  Cross-Language Information Retrieval , 1998, The Springer International Series on Information Retrieval.

[14]  Mark Sanderson,et al.  Relevance Feedback for Cross Language Image Retrieval , 2004, ECIR.

[15]  Douglas W. Oard,et al.  Serving Users in Many Languages: Cross-Language Information Retrieval for Digital Libraries , 1997, D Lib Mag..

[16]  Carol Peters,et al.  Comparative Evaluation of Multilingual Information Access Systems , 2003, Lecture Notes in Computer Science.

[17]  Mark Sanderson,et al.  Measuring a Cross Language Image Retrieval System , 2004, ECIR.

[18]  John S. White,et al.  Envisioning Machine Translation in the Information Future , 2002, Lecture Notes in Computer Science.

[19]  Sergei Nirenburg.  Proceedings of the sixth conference on Applied natural language processing , 2000 .