Learning Translational and Knowledge-based Similarities from Relevance Rankings for Cross-Language Retrieval

Shigehiko Schamoni, Felix Hieber, Artem Sokolov, Stefan Riezler
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
We present an approach to cross-language retrieval that combines dense knowledgebased features and sparse word translations. Both feature types are learned directly from relevance rankings of bilingual documents in a pairwise ranking framework. In large-scale experiments for patent prior art search and cross-lingual retrieval in Wikipedia, our approach yields considerable improvements over learningto-rank with either only dense or only sparse features, and over very competitive baselines that
more » ... mbine state-of-the-art machine translation and retrieval.
doi:10.3115/v1/p14-2080 dblp:conf/acl/SchamoniHSR14 fatcat:fk42avwtpje2pmt76sw276vc7e