Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems

Abstract

Open-domain dialogue systems aim to generate relevant, informative and engaging responses. Seq2seq neural response generation approaches do not have explicit mechanisms to control the content or style of the generated response, and frequently result in uninformative utterances. In this paper, we propose using a dialogue policy to plan the content and style of target responses in the form of an action plan, which includes knowledge sentences related to the dialogue context, targeted dialogue acts, topic information, etc. The attributes within the action plan are obtained by automatically annotating the publicly released Topical-Chat dataset. We condition neural response generators on the action plan which is then realized as target utterances at the turn and sentence levels. We also investigate different dialogue policy models to predict an action plan given the dialogue context. Through automated and human evaluation, we measure the appropriateness of the generated responses and check if the generation models indeed learn to realize the given action plans. We demonstrate that a basic dialogue policy that operates at the sentence level generates better responses in comparison to turn level generation as well as baseline models with no action plan. Additionally the basic dialogue policy has the added effect of controllability.

Link to public dataset

References in corpus (17)

• A Neural Conversational Model
• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• Deep Reinforcement Learning for Dialogue Generation
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• A Persona-Based Neural Conversation Model
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Individual and Domain Adaptation in Sentence Planning for Dialogue
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
• Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
• A Conditional Variational Framework for Dialog Generation
• What makes a good conversation? How controllable attributes affect human judgments
• Alquist 2.0: Alexa Prize Socialbot Based on Sub-Dialogue Models
• SlugBot: Developing a Computational Model andFramework of a Novel Dialogue Genre
• Gunrock: A Social Bot for Complex and Engaging Long Conversations
• Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
• ISO-Standard Domain-Independent Dialogue Act Tagging for Conversational Agents

Cited by in corpus (6)

• DiscASP: A Graph-based ASP System for Finding Relevant Consistent Concepts with Applications to Conversational Socialbots
• Proto: A Neural Cocktail for Generating Appealing Conversations
• Athena: Constructing Dialogues Dynamically with Discourse Constraints
• Semantic-Enhanced Explainable Finetuning for Open-Domain Dialogues
• Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
• Zero-Shot Controlled Generation with Encoder-Decoder Transformers