Self-Supervised Dialogue Learning
arXiv:1907.00448
Abstract
The sequential order of utterances is often meaningful in coherent dialogues, and the order changes of utterances could lead to low-quality and incoherent conversations. We consider the order information as a crucial supervised signal for dialogue learning, which, however, has been neglected by many previous dialogue systems. Therefore, in this paper, we introduce a self-supervised learning task, inconsistent order detection, to explicitly capture the flow of conversation in dialogues. Given a sampled utterance pair triple, the task is to predict whether it is ordered or misordered. Then we propose a sampling-based self-supervised network SSN to perform the prediction with sampled triple references from previous dialogue history. Furthermore, we design a joint learning framework where SSN can guide the dialogue systems towards more coherent and relevant dialogue learning through adversarial training. We demonstrate that the proposed methods can be applied to both open-domain and task-oriented dialogue scenarios, and achieve the new state-of-the-art performance on the OpenSubtitiles and Movie-Ticket Booking datasets.
11pages, 2 figures, accepted to ACL 2019
References in corpus (11)
- Distributed Representations of Words and Phrases and their Compositionality
- Cross-lingual Language Model Pretraining
- A Neural Conversational Model
- Deep Reinforcement Learning for Dialogue Generation
- Professor Forcing: A New Algorithm for Training Recurrent Networks
- Multi-Task Deep Neural Networks for Natural Language Understanding
- Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
- A User Simulator for Task-Completion Dialogues
- Hierarchical Recurrent Attention Network for Response Generation
- LSTM based Conversation Models
- Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning