@InProceedings{10.1007/978-3-642-36973-5_51,
author="Rahimi, Razieh
and Shakery, Azadeh",
editor="Serdyukov, Pavel
and Braslavski, Pavel
and Kuznetsov, Sergei O.
and Kamps, Jaap
and R{\"u}ger, Stefan
and Agichtein, Eugene
and Segalovich, Ilya
and Yilmaz, Emine",
title="A Language Modeling Approach for Extracting Translation Knowledge from Comparable Corpora",
booktitle="Advances in Information Retrieval",
year="2013",
publisher="Springer Berlin Heidelberg",
address="Berlin, Heidelberg",
pages="606--617",
abstract="A main challenge in Cross-Language information retrieval is to estimate a translation language model, as its quality directly affects the retrieval performance. The translation language model is built using translation resources such as bilingual dictionaries, parallel corpora, or comparable corpora. In general, high quality resources may not be available for scarce-resource languages. For these languages, efficient exploitation of commonly available resources such as comparable corpora is considered more crucial. In this paper, we focus on using only comparable corpora to extract translation information more efficiently. We propose a language modeling approach for estimating the translation language model. The proposed method is based on probability distribution estimation, and can be tuned easier in comparison with heuristically adjusted previous work. Experiment results show a significant improvement in the translation quality and CLIR performance compared to the previous approaches.",
isbn="978-3-642-36973-5"
}