Combination Methods for Crosslingual Web Retrieval

Jaap Kamps, Maarten de Rijke, and Börkur Sigurbjörnsson.

Accessing Multilingual Information Repositories: 6th Workshop of the Cross-Language Evaluation Forum, CLEF 2005. Lecture Notes in Computer Science. Volume: 4022. Pages: 856-864. 2006. [Springer] [ACM DL]

We investigate a range of crosslingual web retrieval tasks using the test suite of the CLEF 2005 WebCLEF track, which features a stream of known-item topics in various languages. Our main findings are: (i) straightforward indexing and retrieval is effective for mixed monolingual web retrieval; (ii) standard machine translation methods are effective for bilingual web retrieval; but (iii) standard combination methods are ineffective for multilingual web retrieval; we analyze the failure and suggest an alternative Z-score normalization that leads to effective multilingual retrieval results.

@inproceedings{10.1007/11878773_93,
author = {Kamps, Jaap and de Rijke, Maarten and Sigurbj\"{o}rnsson, B\"{o}rkur},
title = {Combination methods for crosslingual web retrieval},
year = {2005},
isbn = {354045697X},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
url = {https://doi.org/10.1007/11878773_93},
doi = {10.1007/11878773_93},
booktitle = {Proceedings of the 6th International Conference on Cross-Language Evalution Forum: Accessing Multilingual Information Repositories},
pages = {856–864},
numpages = {9},
location = {Vienna, Austria},
series = {CLEF'05}
}