mlsanityData to 14 Oct 2026

Multi-Intent Spoken Language Understanding: Methods, Trends, and Challenges

arXiv 2512.11258 ↗First posted 12 Dec 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-intent spoken language understanding (SLU) involves two tasks: multiple intent detection and slot filling, which jointly handle utterances containing more than one intent. Owing to this characteristic, which closely reflects real-world applications, the task has attracted increasing research attention, and substantial progress has been achieved. However, there remains a lack of a comprehensive and systematic review of existing studies on multi-intent SLU. To this end, this paper presents a survey of recent advances in multi-intent SLU. We provide an in-depth overview of previous research from two perspectives: decoding paradigms and modeling approaches. On this basis, we further compare the performance of representative models and analyze their strengths and limitations. Finally, we discuss the current challenges and outline promising directions for future research. We hope this survey will offer valuable insights and serve as a useful reference for advancing research in multi-intent SLU.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 74 of its 147 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

74 of 147 references.

References · 74

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  7. 2024Mixtral of Expertscited by 1,823
  8. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  9. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  10. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  11. 2020SLURP: A Spoken Language Understanding Resource Packagecited by 198
  12. 2020MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmarkcited by 158
38 more
  1. 2022MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languagescited by 146
  2. 2016Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Fillingcited by 137
  3. 2019Survey on Evaluation Methods for Dialogue Systemscited by 126
  4. 2019A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understandingcited by 107
  5. 2019A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Fillingcited by 85
  6. 2020End-to-End Slot Alignment and Recognition for Cross-Lingual NLUcited by 83
  7. 2023Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learningcited by 72
  8. 2020A Co-Interactive Transformer for Joint Slot Filling and Intent Detectioncited by 61
  9. 2021SpanNER: Named Entity Re-/Recognition as Span Predictioncited by 55
  10. 2018A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Fillingcited by 53
  11. 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
  12. 2020Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Surveycited by 51
  13. 2022Positive-incentive Noisecited by 39
  14. 2023Variational Positive-incentive Noise: How Noise Benefits Modelscited by 38
  15. 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
  16. 2019CM-Net: A Novel Collaborative Memory Network for Spoken Language Understandingcited by 34
  17. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  18. 2024Enhance Vision-Language Alignment with Noisecited by 34
  19. 2021GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Fillingcited by 33
  20. 2024Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noisecited by 25
  21. 2020Few-shot Learning for Multi-label Intent Detectioncited by 20
  22. 2023End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directionscited by 17
  23. 2022MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialoguecited by 15
  24. 2024TeleChat Technical Reportcited by 15
  25. 2025Learn Beneficial Noise as Graph Augmentationcited by 15
  26. 2022Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphscited by 14
  27. 2025Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learningcited by 14
  28. 2021Joint Multiple Intent Detection and Slot Filling via Self-distillationcited by 12
  29. 2024Tele-FLM Technical Reportcited by 12
  30. 2021Towards Joint Intent Detection and Slot Filling via Higher-order Attentioncited by 11
  31. 202452B to 1T: Lessons Learned via Tele-FLM Seriescited by 11
  32. 2021SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Fillingcited by 10
  33. 2022Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Fillingcited by 10
  34. 2025Technical Report of TeleChat2, TeleChat2.5 and T1cited by 10
  35. 2025Explore How to Inject Beneficial Noise in MLLMscited by 10
  36. 2021An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Fillingcited by 9
  37. 2022NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialoguecited by 8
  38. 2021Text is no more Enough! A Benchmark for Profile-based Spoken Language Understandingcited by 7

50 most cited of 74 All 74 (JSON)

Built on by

Not cited yet.