Latent Document Re-Ranking

The problem of re-ranking initial retrieval results exploring the intrinsic structure of documents is widely researched in information retrieval (IR) and has attracted a considerable amount of time and study. However, one of the drawbacks is that those algorithms treat queries and documents separately. Furthermore, most of the approaches are predominantly built upon graph-based methods, which may ignore some hidden information among the retrieval set. This paper proposes a novel document reranking method based on Latent Dirichlet Allocation (LDA) which exploits the implicit structure of the documents with respect to original queries. Rather than relying on graphbased techniques to identify the internal structure, the approach tries to find the latent structure of “topics” or “concepts” in the initial retrieval set. Then we compute the distance between queries and initial retrieval results based on latent semantic information deduced. Empirical results demonstrate that the method can comfortably achieve significant improvement over various baseline systems.