End-to-End Trainable Non-Collaborative Dialog System

Abstract

End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task. While in non-collaborative settings, for example, negotiation and persuasion, users and systems do not share a common goal. As a result, compared to collaborate tasks, people use social content to build rapport and trust in these non-collaborative settings in order to advance their goals. To handle social content, we introduce a hierarchical intent annotation scheme, which can be generalized to different non-collaborative dialog tasks. Building upon TransferTransfo (Wolf et al. 2019), we propose an end-to-end neural network model to generate diverse coherent responses. Our model utilizes intent and semantic slots as the intermediate sentence representation to guide the generation process. In addition, we design a filter to select appropriate responses based on whether these intermediate representations fit the designed task and conversation constraints. Our non-collaborative dialog model guides users to complete the task while simultaneously keeps them engaged. We test our approach on our newly proposed ANTISCAM dataset and an existing PERSUASIONFORGOOD dataset. Both automatic and human evaluations suggest that our model outperforms multiple baselines in these two non-collaborative tasks.

References in corpus (13)

• A Neural Conversational Model
• The Curious Case of Neural Text Degeneration
• 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 Network-based End-to-End Trainable Task-oriented Dialogue System
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Emergent Communication through Negotiation
• Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
• Semantic Parsing for Task Oriented Dialog using Hierarchical Representations
• Decoupling Strategy and Generation in Negotiation Dialogues
• Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
• MOSS: End-to-End Dialog System Framework with Modular Supervision

Cited by in corpus (4)

• Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation
• The Panacea Threat Intelligence and Active Defense Platform
• DEUX: An Attribute-Guided Framework for Sociable Recommendation Dialog Systems
• CRWIZ: A Framework for Crowdsourcing Real-Time Wizard-of-Oz Dialogues