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

05/21/2019
by   Chien-Sheng Wu, et al.
2

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 addition, we show its transferring ability by simulating zero-shot and few-shot dialogue state tracking for unseen domains. TRADE achieves 60.58 accuracy in one of the zero-shot domains, and is able to adapt to few-shot cases without forgetting already trained domains.

READ FULL TEXT
research
05/10/2021

Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking

Zero-shot cross-domain dialogue state tracking (DST) enables us to handl...
research
05/19/2019

Learning to Memorize in Neural Task-Oriented Dialogue Systems

In this thesis, we leverage the neural copy mechanism and memory-augment...
research
02/19/2020

Non-Autoregressive Dialog State Tracking

Recent efforts in Dialogue State Tracking (DST) for task-oriented dialog...
research
04/14/2022

Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking

Dialogue State Tracking (DST) aims to keep track of users' intentions du...
research
12/18/2022

PoE: a Panel of Experts for Generalized Automatic Dialogue Assessment

Chatbots are expected to be knowledgeable across multiple domains, e.g. ...
research
02/22/2020

Data Augmentation for Copy-Mechanism in Dialogue State Tracking

While several state-of-the-art approaches to dialogue state tracking (DS...
research
05/24/2022

Workflow Discovery from Dialogues in the Low Data Regime

Text-based dialogues are now widely used to solve real-world problems. I...

Please sign up or login with your details

Forgot password? Click here to reset