Self-Supervised Dialogue Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Self-Supervised LearningSimilar Papers 제목 키워드 기반
SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation
This paper introduces a novel Self-supervised Fine-grained Dialogue Evaluation framework (SelF-Eval). The core idea is to model the correlation between turn quality and the entire dialogue quality. We first propose a nov…
Contrastive LearningDialogue EvaluationSelf-supervised Speaker Recognition Training Using Human-Machine Dialogues
Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervi…
Contrastive LearningSpeaker RecognitionSelf- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehension
Multi-party dialogue machine reading comprehension (MRC) brings tremendous challenge since it involves multiple speakers at one dialogue, resulting in intricate speaker information flows and noisy dialogue contexts. To a…
Machine Reading ComprehensionQuestion AnsweringReading ComprehensionCSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking
Few-shot dialogue state tracking (DST) is a realistic problem that trains the DST model with limited labeled data. Existing few-shot methods mainly transfer knowledge learned from external labeled dialogue data (e.g., fr…
Dialogue State TrackingMachine Reading ComprehensionQuestion AnsweringReading Comprehension+1Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues
Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is a great challenging task. Existing studies focus on building a context-response matching model wit…
Conversational Response SelectionRetrieval