mlsanityData to 14 Oct 2026

A Survey of Ontology Expansion for Conversational Understanding

arXiv 2410.15019 ↗First posted 19 Oct 2024cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for enhancing the adaptability and robustness of conversational agents. Traditional models rely on static, predefined ontologies, limiting their ability to handle new and unforeseen user needs. This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational understanding. It categorizes the existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp. By examining the methodologies, benchmarks, and challenges associated with these areas, we highlight several emerging frontiers in OnExp to improve agent performance in real-world scenarios and discuss their corresponding challenges. This survey aspires to be a foundational reference for researchers and practitioners, promoting further exploration and innovation in this crucial domain.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 63 of its 118 references that are in the map. First posted on arXiv 19 Oct 2024.

Builds on

63 of 118 references.

References · 63

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  5. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  6. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  7. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
  8. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  9. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  10. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  11. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  12. 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
38 more
  1. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 225
  2. 2016Neural Belief Tracker: Data-Driven Dialogue State Trackingcited by 143
  3. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  4. 2019Multi-class Classification without Multi-class Labelscited by 100
  5. 2021Supporting Clustering with Contrastive Learningcited by 90
  6. 2019A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Fillingcited by 85
  7. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  8. 2023On Learning to Summarize with Large Language Models as Referencescited by 80
  9. 2023Large Language Models Enable Few-Shot Clusteringcited by 72
  10. 2023ClusterLLM: Large Language Models as a Guide for Text Clusteringcited by 70
  11. 2020Discovering New Intents with Deep Aligned Clusteringcited by 68
  12. 2019Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinementcited by 56
  13. 2018Zero-shot User Intent Detection via Capsule Neural Networkscited by 54
  14. 2020Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representationscited by 42
  15. 2017Towards Zero-Shot Frame Semantic Parsing for Domain Scalingcited by 40
  16. 2020Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Productcited by 39
  17. 2019Robust Zero-Shot Cross-Domain Slot Filling with Example Valuescited by 38
  18. 2020Coach: A Coarse-to-Fine Approach for Cross-domain Slot Fillingcited by 38
  19. 2022Generalized Category Discovery with Decoupled Prototypical Networkcited by 35
  20. 2019Few-Shot Representation Learning for Out-Of-Vocabulary Wordscited by 30
  21. 2022DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysiscited by 27
  22. 2018AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experiencecited by 26
  23. 2021TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognitioncited by 24
  24. 2021Generalized Zero-shot Intent Detection via Commonsense Knowledgecited by 21
  25. 2023Exploring Zero and Few-shot Techniques for Intent Classificationcited by 21
  26. 2018Zero-Shot Adaptive Transfer for Conversational Language Understandingcited by 20
  27. 2023Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPTcited by 16
  28. 2023Generalized Category Discovery with Large Language Models in the Loopcited by 15
  29. 2022A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialogcited by 14
  30. 2021Automatic Intent-Slot Induction for Dialogue Systemscited by 13
  31. 2021Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Fillingcited by 13
  32. 2022Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learningcited by 13
  33. 2022Unsupervised Slot Schema Induction for Task-oriented Dialogcited by 11
  34. 2020Encoding Syntactic Knowledge in Transformer Encoder for Intent Detection and Slot Fillingcited by 10
  35. 2022Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discoverycited by 9
  36. 2023A Clustering Framework for Unsupervised and Semi-supervised New Intent Discoverycited by 9
  37. 2019Transfer Learning for Sequence Labeling Using Source Model and Target Datacited by 8
  38. 2023Generative Zero-Shot Prompt Learning for Cross-Domain Slot Filling with Inverse Promptingcited by 8

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancementcited by 10
  2. 2025Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactionscited by 2
  3. 2025LLMs Enable Bag-of-Texts Representations for Short-Text Clusteringcited by 2
  4. 2026METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialoguescited by 2
  5. 2025Dagstuhl Perspectives Workshop 24352 -- Conversational Agents: A Framework for Evaluation (CAFE): Manifestocited by 0
  6. 2025LUMI: Unsupervised Intent Clustering with Multiple Pseudo-Labelscited by 0