Neural Approaches to Conversational AI

2018/09/21 by Jianfeng Gao, Gao, Jianfeng, Michel Galley +3 · 1 voice · 8 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.CL

paper · pdf · doi:10.48550/arxiv.1809.08267

arxiv published 2018/09/21 · arxiv updated 2019/09/10

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.

Cited by

• Context-Aware Intelligent Chatbot Framework Leveraging Mobile Sensing
• A Multimodal Conversational Agent for Tabular Data Analysis
• "Pragmatic Tools or Empowering Friends?" Discovering and Co-Designing Personality-Aligned AI Writing Companions
• A Survey of the State-of-the-Art in Conversational Question Answering Systems
• From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System
• ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience
• Can LLMs Generate High-Quality Task-Specific Conversations?
• HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark

Discussions

• Neural Approaches to Conversational AI [hn, 3 points, 0 comments]

Related

• Recent Progress in Conversational AI
• A survey of neural models for the automatic analysis of conversation: Towards a better integration of the social sciences
• Teaching Machines to Converse
• Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixes
• An Attentional Neural Conversation Model with Improved Specificity