mlsanityData to 7 Oct 2026

Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling

arXiv 2106.07343 ↗First posted 25 May 2021cs.CL cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

In this paper, we investigate few-shot joint learning for dialogue language understanding. Most existing few-shot models learn a single task each time with only a few examples. However, dialogue language understanding contains two closely related tasks, i.e., intent detection and slot filling, and often benefits from jointly learning the two tasks. This calls for new few-shot learning techniques that are able to capture task relations from only a few examples and jointly learn multiple tasks. To achieve this, we propose a similarity-based few-shot learning scheme, named Contrastive Prototype Merging network (ConProm), that learns to bridge metric spaces of intent and slot on data-rich domains, and then adapt the bridged metric space to the specific few-shot domain. Experiments on two public datasets, Snips and FewJoint, show that our model significantly outperforms the strong baselines in one and five shots settings.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 25 May 2021.

Builds on

34 of 50 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  8. 2019BERT for Joint Intent Classification and Slot Fillingcited by 195
  9. 2019A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understandingcited by 106
  10. 2019FewRel 2.0: Towards More Challenging Few-Shot Relation Classificationcited by 94
  11. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 90
  12. 2019A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Fillingcited by 85
22 more
  1. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  2. 2018Joint Slot Filling and Intent Detection via Capsule Neural Networkscited by 73
  3. 2017Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Taggingcited by 71
  4. 2018Sequence-to-Sequence Data Augmentation for Dialogue Language Understandingcited by 67
  5. 2019Induction Networks for Few-Shot Text Classificationcited by 64
  6. 2018Diverse Few-Shot Text Classification with Multiple Metricscited by 61
  7. 2019Few-shot Text Classification with Distributional Signaturescited by 58
  8. 2018Zero-shot User Intent Detection via Capsule Neural Networkscited by 54
  9. 2018A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Fillingcited by 53
  10. 2020SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Fillingcited by 42
  11. 2019Robust Zero-Shot Cross-Domain Slot Filling with Example Valuescited by 38
  12. 2020Coach: A Coarse-to-Fine Approach for Cross-domain Slot Fillingcited by 38
  13. 2019CM-Net: A Novel Collaborative Memory Network for Spoken Language Understandingcited by 34
  14. 2019Multi-Level Matching and Aggregation Network for Few-Shot Relation Classificationcited by 32
  15. 2020Learning to Classify Intents and Slot Labels Given a Handful of Examplescited by 31
  16. 2019Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relationscited by 30
  17. 2020Multi-task learning for natural language processing in the 2020s: where are we going?cited by 27
  18. 2019Neural Snowball for Few-Shot Relation Learningcited by 22
  19. 2020Few-shot Learning for Multi-label Intent Detectioncited by 20
  20. 2020FewJoint: A Few-shot Learning Benchmark for Joint Language Understandingcited by 10
  21. 2018Marrying up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understandingcited by 7
  22. 2018Few-Shot Generalization Across Dialogue Taskscited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 2; 2025: 1.

6 papers.

  1. 2022Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Taggingcited by 5
  2. 2024ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Fillercited by 5
  3. 2023Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Fillingcited by 2
  4. 2024A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLUcited by 2
  5. 2021Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRFcited by 1
  6. 2025Multi-Intent Spoken Language Understanding: Methods, Trends, and Challengescited by 0