Neural Approaches to Conversational AI

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.

IAI MovieBot

“…We base our item collection on the publicly available MovieLens 25M Dataset. 3 This dataset contains 62k movies with 25M ratings and 1M tags assigned by 163k users. We use IMDbPY 4 to retrieve movie details from IMDb, including genres, movie keywords, list of actors, directors, movie duration, plot (summary), release year, IMDb rating with number of votes and links to the movie page and its cover image on IMDb.…”

“…Conversational information access is a rapidly growing eld that has been gaining attention over the past years [1,3]. A conversational recommender system is a task-orientated system that supports its users in accomplishing recommendation-related goals through a multi-turn conversational interaction [4].…”

MALA: Cross-Domain Dialogue Generation with Action Learning

“…Task-oriented dialogue systems complete tasks for users, such as making a restaurant reservation or scheduling a meeting, in a multi-turn conversation (Gao, Galley, and Li 2018;Sun et al 2016;. Recently, end-to-end approaches based on neural encoder-decoder structure have shown promising results (Wen et al 2017b;Madotto, Wu, and Fung 2018).…”

Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning

“…Machine learning for conversational agents has seen great advances (e.g. Tur and Mori, 2011;Gao et al, 2019;Singh et al, 1999;Oh and Rudnicky, 2000;Zen et al, 2009;Reiter and Dale, 2000;Rieser and Lemon, 2010), especially when adopting deep learning models (Deng and Mesnil et al, 2015;Wen et al, 2015Wen et al, , 2017Papangelis et al, 2018;Liu and Lane, 2018b;Li et al, 2017;Williams et al, 2017;Liu and Lane, 2018a). Most of these works, however, suffer from the lack of data availability as it is very challenging to design sample-efficient learning algorithms for problems as complex as training agents capable of meaningful conversations.…”