论文信息 - Merging Different Languages in a Single Document Collection

Merging Different Languages in a Single Document Collection

Multilingual IR is usually carried out with separate collections, each for a language. Once a set of answers have been found in each language, all the sets have to be merged to produce a unique answer list. In our experiments of CLEF2002, we try to implement a different approach, in which the documents in different languages are mixed in the same collection. Indexes are associated with a language tag so as to distinguish homographs in different languages. The indexing and retrieval processes can then be done once for all the documents. No result merging is required. This report describes our first tests in CLEF2002.

Jian-Yun Nie | Fuman Jin

[1] Fredric C. Gey,et al. Cross language information retrieval: a research roadmap , 2002, SIGF.

[2] Changning Huang,et al. Improving query translation for cross-language information retrieval using statistical models , 2001, SIGIR '01.

[3] Jian-Yun Nie,et al. Using Statistical Translation Models for Bilingual IR , 2001, CLEF.

[4] Jian-Yun Nie,et al. Automatic construction of parallel English-Chinese corpus for cross-language information retrieval , 2000, ANLP.

[5] Jacques Savoy,et al. Approaches to collection selection and results merging for distributed information retrieval , 2001, CIKM '01.

[6] Jinxi Xu,et al. Evaluating a probabilistic model for cross-lingual information retrieval , 2001, SIGIR '01.