Data to 7 Oct 2026

Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking

arXiv 2005.00891 ↗First posted 2 May 2020cs.CLcited by 65

Not on the map. Why?

Abstract (arXiv)

Zero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning technique for dialogue state tracking where the in-domain training data are all synthesized from an abstract dialogue model and the ontology of the domain. We show that data augmentation through synthesized data can improve the accuracy of zero-shot learning for both the TRADE model and the BERT-based SUMBT model on the MultiWOZ 2.1 dataset. We show training with only synthesized in-domain data on the SUMBT model can reach about 2/3 of the accuracy obtained with the full training dataset. We improve the zero-shot learning state of the art on average across domains by 21%.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 22; 2023: 12; 2024: 12; 2025: 4.

65 papers.

Sort:

By area:

2021A Survey of Data Augmentation Approaches for NLPcited by 408
2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 231
2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
2022Reasoning Like Program Executorscited by 45
2021Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skillscited by 39
2023SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Promptingcited by 39
2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38
2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38

38 more

2021Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Trackingcited by 35
2021SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systemscited by 34
2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
2022ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examplescited by 29
2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
2022Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Modelscited by 26
2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
2023ChatGPT as your Personal Data Scientistcited by 22
2022Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Trackingcited by 21
2024SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Trackingcited by 17
2021Few Shot Dialogue State Tracking using Meta-learningcited by 16
2021NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulationcited by 16
2022Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialoguecited by 16
2022Robust Dialogue State Tracking with Weak Supervision and Sparse Datacited by 15
2021Generative Conversational Networkscited by 11
2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
2022A Dual Prompt Learning Framework for Few-Shot Dialogue State Trackingcited by 8
2022Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluationcited by 8
2023Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuningcited by 8
2024Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summariescited by 8
2021N-Shot Learning for Augmenting Task-Oriented Dialogue State Trackingcited by 6
2022ThingTalk: An Extensible, Executable Representation Language for Task-Oriented Dialoguescited by 6
2023Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Trackingcited by 6
2024PersonalityChat: Conversation Distillation for Personalized Dialog Modeling with Facts and Traitscited by 6
2024Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Trackingcited by 6
2022Instilling Type Knowledge in Language Models via Multi-Task QAcited by 5
2024Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logiccited by 5
2024Confidence Estimation for LLM-Based Dialogue State Trackingcited by 4
2021High-Quality Diversification for Task-Oriented Dialogue Systemscited by 3
2022MetaASSIST: Robust Dialogue State Tracking with Meta Learningcited by 3
2023UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Promptcited by 3
2024Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPTcited by 3
2025Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMscited by 3
2025DAST: Difficulty-Aware Self-Training on Large Language Modelscited by 3
2022XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Trackingcited by 2
2022Knowledge-Grounded Conversational Data Augmentation with Generative Conversational Networkscited by 2

50 most cited of 65 All 65 (JSON)