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

2017/04/12 by Kai Hui, Hui, Kai, Andrew Yates +5 · 4 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #cs.CL #cs.IR

paper · pdf · doi:10.48550/arxiv.1704.03940

To appear in EMNLP2017

arxiv created 2017/07/21 · arxiv updated 2017/07/25

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.

Cited by

• Controlling Gender Bias in Retrieval via a Backpack Architecture
• REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking
• QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
• A Survey of Long-Document Retrieval in the PLM and LLM Era

Related

• Co-PACRR: A Context-Aware Neural IR Model for Ad-hoc Retrieval
• DE-PACRR: Exploring Layers Inside the PACRR Model
• Neural Networks for Information Retrieval
• Neural Networks for Information Retrieval
• Neural Methods for Effective, Efficient, and Exposure-Aware Information Retrieval