Simultaneous multilingual search for translingual information retrieval Export

@inproceedings{citeulike:5469898, abstract = {We consider the problem of translingual information retrieval, where monolingual searchers issue queries in a different language than the document language(s) and the results must be returned in the language they know, the query language. We present a framework for translingual IR that integrates document translation and query translation into the retrieval model. The corpus is represented as an aligned, jointly indexed "pseudo-parallel" corpus, where each document contains the text of the document along with its translation into the query language. The queries are formulated as multilingual structured queries, where each query term and its translations into the document language(s) are treated as synonym sets. This model leverages simultaneous search in multiple languages against jointly indexed documents to improve the accuracy of results over search using document translation or query translation alone. For query translation, we compared a statistical machine translation (SMT) approach to a dictionary-based approach. We found that using a Wikipedia-derived dictionary for named entities combined with an SMT-based dictionary worked better than SMT alone. Simultaneous multilingual search also has other important features suited to translingual search, since it can provide an indication of poor document translation when a match with the source document is found. We show how close integration of CLIR and SMT allows us to improve result translation in addition to IR results.}, address = {New York, NY, USA}, author = {Parton, Kristen and Mckeown, Kathleen R. and Allan, James and Henestroza, Enrique}, booktitle = {CIKM '08: Proceeding of the 17th ACM conference on Information and knowledge management}, citeulike-article-id = {5469898}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1458082.1458179}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1458082.1458179}, doi = {10.1145/1458082.1458179}, isbn = {978-1-59593-991-3}, keywords = {clir, multilingual-text-retrieval}, location = {Napa Valley, California, USA}, pages = {719--728}, posted-at = {2009-08-18 20:11:10}, priority = {0}, publisher = {ACM}, title = {Simultaneous multilingual search for translingual information retrieval}, url = {http://dx.doi.org/10.1145/1458082.1458179}, year = {2008} }

TY - CONF ID - citeulike:5469898 L3 - citeulike-article-id:5469898 N2 - We consider the problem of translingual information retrieval, where monolingual searchers issue queries in a different language than the document language(s) and the results must be returned in the language they know, the query language. We present a framework for translingual IR that integrates document translation and query translation into the retrieval model. The corpus is represented as an aligned, jointly indexed "pseudo-parallel" corpus, where each document contains the text of the document along with its translation into the query language. The queries are formulated as multilingual structured queries, where each query term and its translations into the document language(s) are treated as synonym sets. This model leverages simultaneous search in multiple languages against jointly indexed documents to improve the accuracy of results over search using document translation or query translation alone. For query translation, we compared a statistical machine translation (SMT) approach to a dictionary-based approach. We found that using a Wikipedia-derived dictionary for named entities combined with an SMT-based dictionary worked better than SMT alone. Simultaneous multilingual search also has other important features suited to translingual search, since it can provide an indication of poor document translation when a match with the source document is found. We show how close integration of CLIR and SMT allows us to improve result translation in addition to IR results. CY - Napa Valley, California, USA SN - 978-1-59593-991-3 AD - New York, NY, USA EP - 728 TI - Simultaneous multilingual search for translingual information retrieval PB - ACM T2 - CIKM '08: Proceeding of the 17th ACM conference on Information and knowledge management SP - 719 KW - clir KW - multilingual-text-retrieval AU - Parton, Kristen AU - Mckeown, Kathleen AU - Allan, James AU - Henestroza, Enrique PY - 2008/// UR - http://dx.doi.org/10.1145/1458082.1458179 ER -