Zero-Shot Dialogue State Tracking via Cross-Task Transfer
arXiv:2109.04655
Abstract
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 \textit{cross-task} knowledge from general question answering (QA) corpora for the zero-shot DST task. Specifically, we propose TransferQA, a transferable generative QA model that seamlessly combines extractive QA and multi-choice QA via a text-to-text transformer framework, and tracks both categorical slots and non-categorical slots in DST. In addition, we introduce two effective ways to construct unanswerable questions, namely, negative question sampling and context truncation, which enable our model to handle "none" value slots in the zero-shot DST setting. The extensive experiments show that our approaches substantially improve the existing zero-shot and few-shot results on MultiWoz. Moreover, compared to the fully trained baseline on the Schema-Guided Dialogue dataset, our approach shows better generalization ability in unseen domains.
EMNLP 2021
References in corpus (13)
- Decoupled Weight Decay Regularization
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- Prefix-Tuning: Optimizing Continuous Prompts for Generation
- Building a Conversational Agent Overnight with Dialogue Self-Play
- A Simple Language Model for Task-Oriented Dialogue
- SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
- DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue
- Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering
- CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
- BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
- Efficient Dialogue State Tracking by Selectively Overwriting Memory
- From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
- MA-DST: Multi-Attention Based Scalable Dialog State Tracking