Litcius/Paper detail

Training Effective Neural CLIR by Bridging the Translation Gap

Hamed Bonab, Sheikh Muhammad Sarwar, James Allan

202035 citationsDOI

Abstract

We introduce Smart Shuffling, a cross-lingual embedding (CLE) method that draws from statistical word alignment approaches to leverage dictionaries, producing dense representations that are significantly more effective for cross-language information retrieval (CLIR) than prior CLE methods. This work is motivated by the observation that although neural approaches are successful for monolingual IR, they are less effective in the cross-lingual setting. We hypothesize that neural CLIR fails because typical cross-lingual embeddings "translate" query terms into related terms -- i.e., terms that appear in a similar context -- in addition to or sometimes rather than synonyms in the target language. Adding related terms to a query (i.e., query expansion) can be valuable for retrieval, but must be mitigated by also focusing on the starting query. We find that prior neural CLIR models are unable to bridge the translation gap, apparently producing queries that drift from the intent of the source query.

Topics & Concepts

Computer scienceBridging (networking)ShufflingLeverage (statistics)Artificial intelligenceNatural language processingQuery expansionWord embeddingEmbeddingInformation retrievalProgramming languageComputer networkNatural Language Processing TechniquesTopic ModelingBiomedical Text Mining and Ontologies