“They Are Out There, If You Know Where to Look”: Mining Transliterations of OOV Query Terms for Cross-Language Information Retrieval Export

@incollection{citeulike:5293110, abstract = {It is well known that the use of a good Machine Transliteration system improves the retrieval performance of Cross-Language Information Retrieval (CLIR) systems when the query and document languages have different orthography and phonetic alphabets. However, the effectiveness of a Machine Transliteration system in CLIR is limited by its ability to produce relevant transliterations, i.e. those transliterations which are actually present in the relevant documents. In this work, we propose a new approach to the problem of finding transliterations for out-of-vocabulary query terms. Instead of ” generating” the transliterations using a Machine Transliteration system, we ” mine” them, using a transliteration similarity model, from the top CLIR results for the query. We treat the query and each of the top results as ” comparable” documents and search for transliterations in these comparable document pairs. We demonstrate the effectiveness of our approach using queries in two languages from two different linguistic families to retrieve English documents from two standard CLEF collections. We also compare our results with those of a state-of-the-art Machine Transliteration system.}, author = {Udupa, Raghavendra and Saravanan and Bakalov, Anton and Bhole, Abhijit}, citeulike-article-id = {5293110}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-642-00958-7_39}, citeulike-linkout-1 = {http://www.springerlink.com/content/h83511340k2gg314}, doi = {10.1007/978-3-642-00958-7_39}, journal = {Advances in Information Retrieval}, keywords = {clir, information\_retrieval, machine-translation}, pages = {437--448}, posted-at = {2009-07-28 18:18:16}, priority = {0}, title = { ” They Are Out There, If You Know Where to Look”: Mining Transliterations of OOV Query Terms for Cross-Language Information Retrieval}, url = {http://dx.doi.org/10.1007/978-3-642-00958-7_39}, year = {2009} }

TY - CHAP ID - citeulike:5293110 L3 - citeulike-article-id:5293110 N2 - It is well known that the use of a good Machine Transliteration system improves the retrieval performance of Cross-Language Information Retrieval (CLIR) systems when the query and document languages have different orthography and phonetic alphabets. However, the effectiveness of a Machine Transliteration system in CLIR is limited by its ability to produce relevant transliterations, i.e. those transliterations which are actually present in the relevant documents. In this work, we propose a new approach to the problem of finding transliterations for out-of-vocabulary query terms. Instead of “generating” the transliterations using a Machine Transliteration system, we “mine” them, using a transliteration similarity model, from the top CLIR results for the query. We treat the query and each of the top results as “comparable” documents and search for transliterations in these comparable document pairs. We demonstrate the effectiveness of our approach using queries in two languages from two different linguistic families to retrieve English documents from two standard CLEF collections. We also compare our results with those of a state-of-the-art Machine Transliteration system. JF - Advances in Information Retrieval EP - 448 TI - “They Are Out There, If You Know Where to Look”: Mining Transliterations of OOV Query Terms for Cross-Language Information Retrieval SP - 437 KW - clir KW - information_retrieval KW - machine-translation AU - Udupa, Raghavendra AU - Saravanan AU - Bakalov, Anton AU - Bhole, Abhijit PY - 2009/// UR - http://dx.doi.org/10.1007/978-3-642-00958-7_39 ER -