Abstract

Statistical translation models and latent semantic analysis (LSA) are two effective approaches to exploit click-through data for web search ranking. This paper presents two document ranking models that combine both approaches by explicitly modeling word-pairs. The first model, called Pair-Model, is a monolingual ranking model based on word pairs that are derived from click-through data. It maps queries and documents into a concept space spanned by these word pairs. The second model, called Bilingual Paired Topic Model (BPTM), uses bilingual word pairs and jointly models a bilingual query-document collection. This model maps queries and documents in multiple languages into a lower dimensional semantic subspace. Experimental results on web search task show that they significantly outperform the state-of-the-art baseline models, and the best result is obtained by interpolating PairModel and BPTM.

Citations