Proactive Human-Machine Conversation with Explicit Conversation Goals

Abstract

Though great progress has been made for human-machine conversation, current dialogue system is still in its infancy: it usually converses passively and utters words more as a matter of response, rather than on its own initiatives. In this paper, we take a radical step towards building a human-like conversational agent: endowing it with the ability of proactively leading the conversation (introducing a new topic or maintaining the current topic). To facilitate the development of such conversation systems, we create a new dataset named DuConv where one acts as a conversation leader and the other acts as the follower. The leader is provided with a knowledge graph and asked to sequentially change the discussion topics, following the given conversation goal, and meanwhile keep the dialogue as natural and engaging as possible. DuConv enables a very challenging task as the model needs to both understand dialogue and plan over the given knowledge graph. We establish baseline results on this dataset (about 270K utterances and 30k dialogues) using several state-of-the-art models. Experimental results show that dialogue models that plan over the knowledge graph can make full use of related knowledge to generate more diverse multi-turn conversations. The baseline systems along with the dataset are publicly available

arXiv commentAccepted by ACL 2019

References in corpus (5)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• Towards Deep Conversational Recommendations
• Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
• Neural Generative Question Answering

Cited by in corpus (14)

• Challenges in Building Intelligent Open-domain Dialog Systems
• NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation
• PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation
• Sensible Agent: A Framework for Unobtrusive Interaction with Proactive AR Agents
• Discovering Dialog Structure Graph for Open-Domain Dialog Generation
• Robust Dialogue Utterance Rewriting as Sequence Tagging
• A Large-Scale Chinese Short-Text Conversation Dataset
• Domain-Adaptive Pretraining Methods for Dialogue Understanding
• Keyword-Guided Neural Conversational Model
• Wizard of Search Engine: Access to Information Through Conversations with Search Engines
• Cross Copy Network for Dialogue Generation
• Conversational Semantic Role Labeling
• DCA: Diversified Co-Attention towards Informative Live Video Commenting
• Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent