Neural Information Retrieval: A Literature Review

TL;DR

This paper surveys recent neural network approaches to Information Retrieval, highlighting successes, challenges, and future directions in leveraging learned representations for improved IR performance.

Contribution

It provides a comprehensive overview of neural IR research, emphasizing neural embeddings and identifying key obstacles and promising future research directions.

Findings

Neural IR has shown promising results with learned representations.

Challenges include scalability and interpretability issues.

Future research may focus on integrating neural methods with traditional IR techniques.

Abstract

A recent "third wave" of Neural Network (NN) approaches now delivers state-of-the-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing. Because these modern NNs often comprise multiple interconnected layers, this new NN research is often referred to as deep learning. Stemming from this tide of NN work, a number of researchers have recently begun to investigate NN approaches to Information Retrieval (IR). While deep NNs have yet to achieve the same level of success in IR as seen in other areas, the recent surge of interest and work in NNs for IR suggest that this state of affairs may be quickly changing. In this work, we survey the current landscape of Neural IR research, paying special attention to the use of learned representations of queries and documents (i.e., neural embeddings). We highlight the successes of neural IR thus far, catalog obstacles to its wider adoption, and suggest potentially promising directions for future research.