Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking
With the demanding need for deploying dialogue systems in new domains with less cost, zero-shot dialogue state tracking (DST), which tracks user's requirements in task-oriented dialogues without training on desired domains, draws attention increasingly. Although prior works have leveraged question-answering (QA) data to reduce the need for in-domain training in DST, they fail to explicitly model knowledge transfer and fusion for tracking dialogue states. To address this issue, we propose CoFunDST, which is trained on domain-agnostic QA datasets and directly uses candidate choices of slot-values as knowledge for zero-shot dialogue-state generation, based on a T5 pre-trained language model. Specifically, CoFunDST selects highly-relevant choices to the reference context and fuses them to initialize the decoder to constrain the model outputs. Our experimental results show that our proposed model achieves outperformed joint goal accuracy compared to existing zero-shot DST approaches in most domains on the MultiWOZ 2.1. Extensive analyses demonstrate the effectiveness of our proposed approach for improving zero-shot DST learning from QA.
Code (1)
Tasks
DecoderDialogue State TrackingLanguage ModelingLanguage ModellingQuestion AnsweringTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Zero-Shot Dialogue State Tracking via Cross-Task Transfer
Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the \t…
Dialogue State TrackingQuestion AnsweringTransfer LearningNeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation
We propose NeuralWOZ, a novel dialogue collection framework that uses model-based dialogue simulation. NeuralWOZ has two pipelined models, Collector and Labeler. Collector generates dialogues from (1) user's goal instruc…
Dialogue State TrackingMultiple-choiceTransfer LearningMulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation
Building dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such…
Data AugmentationDialogue GenerationText GenerationLeveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot description enhanced g…
Dialogue State TrackingTransfer LearningLeveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot descriptions enhanced generative approach for ze…
Dialogue State TrackingTransfer Learning