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

## TL;DR

PACRR is a neural information retrieval model that effectively captures position-dependent interactions like proximity and term dependencies, leading to improved relevance matching in web search tasks.

## Contribution

The paper introduces PACRR, a novel neural IR model that incorporates position-aware features for enhanced relevance matching, addressing limitations of previous models.

## Key findings

- PACRR outperforms existing models on TREC Web Track data.
- Position-aware modeling improves relevance assessment.
- Extensive experiments validate the effectiveness of PACRR.

## Abstract

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.