Teacher-Student Framework Enhanced Multi-domain Dialogue Generation
arXiv:1908.07137
Abstract
Dialogue systems dealing with multi-domain tasks are highly required. How to record the state remains a key problem in a task-oriented dialogue system. Normally we use human-defined features as dialogue states and apply a state tracker to extract these features. However, the performance of such a system is limited by the error propagation of a state tracker. In this paper, we propose a dialogue generation model that needs no external state trackers and still benefits from human-labeled semantic data. By using a teacher-student framework, several teacher models are firstly trained in their individual domains, learn dialogue policies from labeled states. And then the learned knowledge and experience are merged and transferred to a universal student model, which takes raw utterance as its input. Experiments show that the dialogue system trained under our framework outperforms the one uses a belief tracker.
arXiv commentOfficial Version: arXiv:2005.10450
References in corpus (5)
- Distilling the Knowledge in a Neural Network
- Multilingual Neural Machine Translation with Knowledge Distillation
- Attention with Intention for a Neural Network Conversation Model
- Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems
- Toward Scalable Neural Dialogue State Tracking Model
Cited by in corpus (9)
- SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
- Task-Oriented Dialogue System as Natural Language Generation
- MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
- Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language
- SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System
- Pretraining the Noisy Channel Model for Task-Oriented Dialogue
- MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
- Transferable Dialogue Systems and User Simulators
- UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues