Pseudo-Query Reformulation

TL;DR

This paper introduces a flexible framework for automatic query reformulation using discrete optimization, modeling it as a graph search problem to enhance retrieval performance across various datasets.

Contribution

It proposes a novel pseudo-query reformulation framework that leverages graph search and performance prediction heuristics for improved query rewriting.

Findings

Effective on multiple datasets

Integrates performance prediction heuristics

Improves retrieval ranking

Abstract

Automatic query reformulation refers to rewriting a user's original query in order to improve the ranking of retrieval results compared to the original query. We present a general framework for automatic query reformulation based on discrete optimization. Our approach, referred to as pseudo-query reformulation, treats automatic query reformulation as a search problem over the graph of unweighted queries linked by minimal transformations (e.g. term additions, deletions). This framework allows us to test existing performance prediction methods as heuristics for the graph search process. We demonstrate the effectiveness of the approach on several publicly available datasets.