PACRR: A Position-Aware Neural IR Model for Relevance Matching
This work addresses a bottleneck in neural IR for improving relevance matching, though it appears incremental as it builds on prior models that captured unigram matches.
The authors tackled the problem of modeling position-dependent interactions like proximity and term dependencies in neural information retrieval, and their proposed PACRR model achieved better results on six years of TREC Web Track data.
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 aiming at better modeling position-dependent interactions between a query and a document. Extensive experiments on six years' TREC Web Track data confirm that the proposed model yields better results under multiple benchmarks.