Profile Consistency Identification for Open-domain Dialogue Agents

Abstract

Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans. Existing studies on improving attribute consistency mainly explored how to incorporate attribute information in the responses, but few efforts have been made to identify the consistency relations between response and attribute profile. To facilitate the study of profile consistency identification, we create a large-scale human-annotated dataset with over 110K single-turn conversations and their key-value attribute profiles. Explicit relation between response and profile is manually labeled. We also propose a key-value structure information enriched BERT model to identify the profile consistency, and it gained improvements over strong baselines. Further evaluations on downstream tasks demonstrate that the profile consistency identification model is conducive for improving dialogue consistency.

EMNLP20

References in corpus (5)

• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• TabFact: A Large-scale Dataset for Table-based Fact Verification
• DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
• Personalized Dialogue Generation with Diversified Traits
• Generating Persona Consistent Dialogues by Exploiting Natural Language Inference

Cited by in corpus (5)

• BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
• A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation
• Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona
• Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency
• Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System