Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns
Not on the map. Why?
Abstract (arXiv)
Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata. Augmenting the training set with human or synthetic schema paraphrases improves the model robustness to these variations but can be either costly or difficult to control. We propose to circumvent these issues by grounding the state tracking model in knowledge-seeking turns collected from the dialogue corpus as well as the schema. Including these turns in prompts during finetuning and inference leads to marked improvements in model robustness, as demonstrated by large average joint goal accuracy and schema sensitivity improvements on SGD and SGD-X.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 23 Sep 2023.
Builds on
25 of 35 references.
References · 25
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
- 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
- 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
- 2021Deduplicating Training Data Makes Language Models Bettercited by 705
- 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
- 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
- 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
- 2016Neural Belief Tracker: Data-Driven Dialogue State Trackingcited by 142
- 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
- 2021Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systemscited by 73
- 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
13 more
- 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
- 2019Dialog State Tracking: A Neural Reading Comprehension Approachcited by 62
- 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
- 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
- 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
- 2020Pre-training Text-to-Text Transformers for Concept-centric Common Sensecited by 42
- 2021SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systemscited by 34
- 2022A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generationcited by 28
- 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
- 2022Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialoguecited by 16
- 2021On Robustness of Neural Semantic Parserscited by 14
- 2022Unsupervised Slot Schema Induction for Task-oriented Dialogcited by 11
- 2022A Multi-Task BERT Model for Schema-Guided Dialogue State Trackingcited by 5
Built on by
Citing papers per year: 2025: 1.
1 paper.