Neural Approaches to Conversational AI

Abstract

The present paper surveys neural approaches to conversational AI that have been developed in the last few years. We group conversational systems into three categories: (1) question answering agents, (2) task-oriented dialogue agents, and (3) chatbots. For each category, we present a review of state-of-the-art neural approaches, draw the connection between them and traditional approaches, and discuss the progress that has been made and challenges still being faced, using specific systems and models as case studies.

arXiv commentFoundations and Trends in Information Retrieval (95 pages)

Cited by in corpus (15)

• Medical Deep Learning -- A systematic Meta-Review
• Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
• Query Resolution for Conversational Search with Limited Supervision
• UX Research on Conversational Human-AI Interaction: A Literature Review of the ACM Digital Library
• Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
• Submitting surveys via a conversational interface: an evaluation of user acceptance and approach effectiveness
• DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following
• Harnessing Evolution of Multi-Turn Conversations for Effective Answer Retrieval
• Natural Language Interfaces to Data
• NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation
• MALA: Cross-Domain Dialogue Generation with Action Learning
• Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems
• IAI MovieBot: A Conversational Movie Recommender System
• A Re-classification of Information Seeking Tasks and Their Computational Solutions
• DAGFiNN: A Conversational Conference Assistant