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

ACL ID P14-2080
Title Learning Translational and Knowledge-based Similarities from Relevance Rankings for Cross-Language Retrieval
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

We present an approach to cross-language retrieval that combines dense knowledge- based features and sparse word transla- tions. Both feature types are learned di- rectly from relevance rankings of bilin- gual documents in a pairwise ranking framework. In large-scale experiments for patent prior art search and cross-lingual re- trieval in Wikipedia, our approach yields considerable improvements over learning- to-rank with either only dense or only sparse features, and over very competitive baselines that combine state-of-the-art ma- chine translation and retrieval.