PACRR: A Position-Aware Neural IR Model for Relevance Matching

In order to adopt deep learning for information retrieval, models are needed that can capture all relevant information required to assess the relevance of a document to a given user query. While previous works have successfully captured unigram term matches, how to fully employ position-dependent information such as proximity and term dependencies has been insufficiently explored. In this work, we propose a novel neural IR model named PACRR (Position-Aware Convolutional-Recurrent Relevance), aiming at better modeling position-dependent interactions between a query and a document via convolutional layers as well as recurrent layers. Extensive experiments on six years' TREC Web Track data confirm that the proposed model yields better results under different benchmarks