A Hybrid Retrieval-Generation Neural Conversation Model

Abstract

Intelligent personal assistant systems that are able to have multi-turn conversations with human users are becoming increasingly popular. Most previous research has been focused on using either retrieval-based or generation-based methods to develop such systems. Retrieval-based methods have the advantage of returning fluent and informative responses with great diversity. However, the performance of the methods is limited by the size of the response repository. On the other hand, generation-based methods can produce highly coherent responses on any topics. But the generated responses are often generic and not informative due to the lack of grounding knowledge. In this paper, we propose a hybrid neural conversation model that combines the merits of both response retrieval and generation methods. Experimental results on Twitter and Foursquare data show that the proposed model outperforms both retrieval-based methods and generation-based methods (including a recently proposed knowledge-grounded neural conversation model) under both automatic evaluation metrics and human evaluation. We hope that the findings in this study provide new insights on how to integrate text retrieval and text generation models for building conversation systems.

arXiv commentAccepted as a Full Paper in CIKM 2019. 10 pages

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• A Neural Conversational Model
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• End-to-End Neural Ad-hoc Ranking with Kernel Pooling
• Deep Reinforcement Learning for Dialogue Generation
• A Diversity-Promoting Objective Function for Neural Conversation Models
• An Information Retrieval Approach to Short Text Conversation
• A Persona-Based Neural Conversation Model
• Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
• deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
• Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
• Response Generation by Context-aware Prototype Editing
• A Deep Look into Neural Ranking Models for Information Retrieval
• Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce

Cited by in corpus (6)

• Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
• Introducing MANtIS: a novel Multi-Domain Information Seeking Dialogues Dataset
• ATOM: Commit Message Generation Based on Abstract Syntax Tree and Hybrid Ranking
• IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
• Curriculum Learning Strategies for IR: An Empirical Study on Conversation Response Ranking
• Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations