Semantic Modelling with Long-Short-Term Memory for Information Retrieval

TL;DR

This paper introduces a novel approach using Long-Short-Term Memory networks to incorporate long-term context in web document retrieval, significantly improving performance over traditional bag-of-words methods.

Contribution

It is the first application of LSTM to IR, demonstrating how sequence modeling enhances retrieval accuracy by capturing contextual dependencies.

Findings

Outperforms existing IR methods on Bing search data

Addresses lexical mismatch issues effectively

Models long-term context for improved retrieval

Abstract

In this paper we address the following problem in web document and information retrieval (IR): How can we use long-term context information to gain better IR performance? Unlike common IR methods that use bag of words representation for queries and documents, we treat them as a sequence of words and use long short term memory (LSTM) to capture contextual dependencies. To the best of our knowledge, this is the first time that LSTM is applied to information retrieval tasks. Unlike training traditional LSTMs, the training strategy is different due to the special nature of information retrieval problem. Experimental evaluation on an IR task derived from the Bing web search demonstrates the ability of the proposed method in addressing both lexical mismatch and long-term context modelling issues, thereby, significantly outperforming existing state of the art methods for web document retrieval task.