Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

Abstract

Over-dependence on domain ontology and lack of knowledge sharing across domains are two practical and yet less studied problems of dialogue state tracking. Existing approaches generally fall short in tracking unknown slot values during inference and often have difficulties in adapting to new domains. In this paper, we propose a Transferable Dialogue State Generator (TRADE) that generates dialogue states from utterances using a copy mechanism, facilitating knowledge transfer when predicting (domain, slot, value) triplets not encountered during training. Our model is composed of an utterance encoder, a slot gate, and a state generator, which are shared across domains. Empirical results demonstrate that TRADE achieves state-of-the-art joint goal accuracy of 48.62% for the five domains of MultiWOZ, a human-human dialogue dataset. In addition, we show its transferring ability by simulating zero-shot and few-shot dialogue state tracking for unseen domains. TRADE achieves 60.58% joint goal accuracy in one of the zero-shot domains, and is able to adapt to few-shot cases without forgetting already trained domains.

The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019)

References in corpus (7)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• The Natural Language Decathlon: Multitask Learning as Question Answering
• Overcoming Catastrophic Forgetting by Incremental Moment Matching
• A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
• Toward Continual Learning for Conversational Agents

Cited by in corpus (26)

• A Simple Language Model for Task-Oriented Dialogue
• Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems
• Structured Prediction as Translation between Augmented Natural Languages
• Task-Oriented Dialogue System as Natural Language Generation
• Recent Advances and Challenges in Task-oriented Dialog System
• Attention over Parameters for Dialogue Systems
• MALA: Cross-Domain Dialogue Generation with Action Learning
• From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
• Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems
• MA-DST: Multi-Attention Based Scalable Dialog State Tracking
• Speech-language Pre-training for End-to-end Spoken Language Understanding
• The SPPD System for Schema Guided Dialogue State Tracking Challenge
• User Memory Reasoning for Conversational Recommendation
• Data Augmentation for Copy-Mechanism in Dialogue State Tracking
• Robustness through Data Augmentation Loss Consistency
• Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking
• Improving Longer-range Dialogue State Tracking
• Slot Self-Attentive Dialogue State Tracking
• ShopTalk: A System for Conversational Faceted Search
• A Joint and Domain-Adaptive Approach to Spoken Language Understanding
• MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert
• X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing
• An Adversarial Learning based Multi-Step Spoken Language Understanding System through Human-Computer Interaction
• Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking
• Variational Reward Estimator Bottleneck: Learning Robust Reward Estimator for Multi-Domain Task-Oriented Dialog
• Efficient Dialogue State Tracking by Masked Hierarchical Transformer