Learning to Rank Bilingual Document Based on Document Similarity
HUANG Jian
Abstract：The problem of learning to rank bilingual documents is addressed. Ranking is an essential part in information re-trieval.Ranking documents in monolingual context using machine learning has been studied a lot,but learning to rank bilingual doc-uments has not been investigated much yet.Bilingual documents are written in different languages,they can't be processed by using existing monolingual methods directly.In this paper a bilingual learning is proposed to rank model which utilizes monolingual model to give ranking score for documents in monolingual context as a base component.A word embedding approach is introduced to mea-sure document similarity in bilingual context,through which a relationship between documents in both languages can be made.We simply translate the query to foreign language at a phrase level to filter foreign language documents.Experiments show that our mod-el is effective in ranking bilingual documents in both English-Chinese context and English-Vietnamese context.
Keywords：learning to rankinformation retrievaldocument similarityquery translationbilingual context
Publication Date：2017-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1986-1989,2017 )