mlsanityData to 7 Oct 2026

Unsupervised Slot Schema Induction for Task-oriented Dialog

arXiv 2205.04515 ↗First posted 9 May 2022cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

Carefully-designed schemas describing how to collect and annotate dialog corpora are a prerequisite towards building task-oriented dialog systems. In practical applications, manually designing schemas can be error-prone, laborious, iterative, and slow, especially when the schema is complicated. To alleviate this expensive and time consuming process, we propose an unsupervised approach for slot schema induction from unlabeled dialog corpora. Leveraging in-domain language models and unsupervised parsing structures, our data-driven approach extracts candidate slots without constraints, followed by coarse-to-fine clustering to induce slot types. We compare our method against several strong supervised baselines, and show significant performance improvement in slot schema induction on MultiWoz and SGD datasets. We also demonstrate the effectiveness of induced schemas on downstream applications including dialog state tracking and response generation.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 33 of its 74 references that are in the map. First posted on arXiv 9 May 2022.

Builds on

33 of 74 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  3. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  4. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  5. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  6. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  7. 2016Variational Deep Embedding: An Unsupervised and Generative Approach to Clusteringcited by 219
  8. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 201
  9. 2020TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialoguecited by 185
  10. 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
  11. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  12. 2019A Discrete Hard EM Approach for Weakly Supervised Question Answeringcited by 78
21 more
  1. 2020Span-based Semantic Parsing for Compositional Generalizationcited by 77
  2. 2019Compound Probabilistic Context-Free Grammars for Grammar Inductioncited by 76
  3. 2021Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systemscited by 73
  4. 2017Zero-Shot Transfer Learning for Event Extractioncited by 66
  5. 2018Simple Unsupervised Keyphrase Extraction using Sentence Embeddingscited by 62
  6. 2017Neural Language Modeling by Jointly Learning Syntax and Lexiconcited by 57
  7. 2020PMI-Masking: Principled masking of correlated spanscited by 54
  8. 2019Visually Grounded Neural Syntax Acquisitioncited by 48
  9. 2020Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Inductioncited by 47
  10. 2019Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attentioncited by 43
  11. 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
  12. 2020Asking without Telling: Exploring Latent Ontologies in Contextual Representationscited by 34
  13. 2020ConVEx: Data-Efficient and Few-Shot Slot Labelingcited by 22
  14. 2019MIDAS: A Dialog Act Annotation Scheme for Open Domain Human Machine Spoken Conversationscited by 20
  15. 2021Video-aided Unsupervised Grammar Inductioncited by 17
  16. 2021Corpus-based Open-Domain Event Type Inductioncited by 17
  17. 2020Probing Task-Oriented Dialogue Representation from Language Modelscited by 15
  18. 2020Dialogue State Induction Using Neural Latent Variable Modelscited by 10
  19. 2021Semantic Frame Induction using Masked Word Embeddings and Two-Step Clusteringcited by 9
  20. 2019Dependency Parsing for Spoken Dialog Systemscited by 5
  21. 2021Neural Sequence Segmentation as Determining the Leftmost Segmentscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 3; 2024: 2; 2025: 2.

11 papers.

  1. 2022Workflow Discovery from Dialogues in the Low Data Regimecited by 12
  2. 2022AnyTOD: A Programmable Task-Oriented Dialog Systemcited by 10
  3. 2024A Survey of Ontology Expansion for Conversational Understandingcited by 6
  4. 2022Dialogue Term Extraction using Transfer Learning and Topological Data Analysiscited by 5
  5. 2022Knowledge-grounded Dialog State Trackingcited by 5
  6. 2023NatCS: Eliciting Natural Customer Support Dialoguescited by 5
  7. 2023Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learningcited by 4
  8. 2024Transforming Slot Schema Induction with Generative Dialogue State Inferencecited by 3
  9. 2025Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactionscited by 2
  10. 2023Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turnscited by 1
  11. 2025Text-to-SQL Task-oriented Dialogue Ontology Constructioncited by 1