Neural Approaches to Conversational Information Retrieval

TL;DR

This paper surveys recent neural approaches to conversational information retrieval, highlighting advances in deep learning that enable more natural and human-centric multi-turn interactions in IR systems.

Contribution

It provides a comprehensive overview of recent neural methods in CIR, based on a tutorial, serving as an accessible resource for researchers and developers.

Findings

Recent neural models improve multi-turn conversational IR

Deep learning advances enhance natural language understanding in CIR

The survey identifies key challenges and future directions in neural CIR

Abstract

A conversational information retrieval (CIR) system is an information retrieval (IR) system with a conversational interface which allows users to interact with the system to seek information via multi-turn conversations of natural language, in spoken or written form. Recent progress in deep learning has brought tremendous improvements in natural language processing (NLP) and conversational AI, leading to a plethora of commercial conversational services that allow naturally spoken and typed interaction, increasing the need for more human-centric interactions in IR. As a result, we have witnessed a resurgent interest in developing modern CIR systems in both research communities and industry. This book surveys recent advances in CIR, focusing on neural approaches that have been developed in the last few years. This book is based on the authors' tutorial at SIGIR'2020 (Gao et al., 2020b), with IR and NLP communities as the primary target audience. However, audiences with other background, such as machine learning and human-computer interaction, will also find it an accessible introduction to CIR. We hope that this book will prove a valuable resource for students, researchers, and software developers. This manuscript is a working draft. Comments are welcome.