Learning to Reformulate the Queries on the WEB

TL;DR

This paper presents an end-to-end neural network model that automatically reformulates web search queries using anchor phrase data, significantly improving retrieval performance.

Contribution

It introduces a novel character-level sequence-to-sequence model trained on large-scale anchor phrase data for query reformulation, advancing beyond traditional phrase-based methods.

Findings

Reformulated queries improve retrieval effectiveness.

The model leverages large-scale anchor phrase data.

Significant performance gains demonstrated on TREC collections.

Abstract

Inability of the naive users to formulate appropriate queries is a fundamental problem in web search engines. Therefore, assisting users to issue more effective queries is an important way to improve users' happiness. One effective approach is query reformulation, which generates new effective queries according to the current query issued by users. Previous researches typically generate words and phrases related to the original query. Since the definition of query reformulation is quite general, it is completely difficult to develop a uniform term-based approach for this problem. This paper uses readily available data, particularly over one billion anchor phrases in Clueweb09 corpus, in order to learn an end-to-end encoder-decoder model to automatically generate effective queries. Following successful researches in the field of sequence to sequence models, we employ a character-level convolutional neural network with max-pooling at encoder and an attention-based recurrent neural network at decoder. The whole model learned in an unsupervised end-to-end manner.Experiments on TREC collections show that the reformulated queries automatically generated by the proposed solution can significantly improve the retrieval performance.