mlsanityData to 13 Oct 2026

Few-shot Intent Classification and Slot Filling with Retrieved Examples

arXiv 2104.05763 ↗First posted 12 Apr 2021cs.CLcited by 35

Not on the map. Why?

Abstract (arXiv)

Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain. In this paper, we explore retrieval-based methods for intent classification and slot filling tasks in few-shot settings. Retrieval-based methods make predictions based on labeled examples in the retrieval index that are similar to the input, and thus can adapt to new domains simply by changing the index without having to retrain the model. However, it is non-trivial to apply such methods on tasks with a complex label space like slot filling. To this end, we propose a span-level retrieval method that learns similar contextualized representations for spans with the same label via a novel batch-softmax objective. At inference time, we use the labels of the retrieved spans to construct the final structure with the highest aggregated score. Our method outperforms previous systems in various few-shot settings on the CLINC and SNIPS benchmarks.

Key facts. Cited by 35 papers in the map (data through 13 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

33 of 44 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,221
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,870
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,011
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,838
  6. 2018Deep contextualized word representationscited by 2,286
  7. 2016Matching Networks for One Shot Learningcited by 2,251
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,131
  9. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 833
  10. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 797
  11. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 545
  12. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 381
21 more
  1. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  2. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 314
  3. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  4. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
  5. 2019Learning Dense Representations for Entity Retrievalcited by 122
  6. 2020Revisiting Training Strategies and Generalization Performance in Deep Metric Learningcited by 100
  7. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 91
  8. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  9. 2018Few-shot classification in Named Entity Recognition Taskcited by 64
  10. 2019Induction Networks for Few-Shot Text Classificationcited by 64
  11. 2018Guiding Neural Machine Translation with Retrieved Translation Piecescited by 63
  12. 2018Diverse Few-Shot Text Classification with Multiple Metricscited by 61
  13. 2019Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmaxcited by 58
  14. 2020Learning to Classify Intents and Slot Labels Given a Handful of Examplescited by 31
  15. 2019Text Generation with Exemplar-based Adaptive Decodingcited by 28
  16. 2019Label-Agnostic Sequence Labeling by Copying Nearest Neighborscited by 27
  17. 2020A Cross-Task Analysis of Text Span Representationscited by 21
  18. 2019MIDAS: A Dialog Act Annotation Scheme for Open Domain Human Machine Spoken Conversationscited by 20
  19. 2020Example-Based Named Entity Recognitioncited by 19
  20. 2019Gunrock: A Social Bot for Complex and Engaging Long Conversationscited by 14
  21. 2020Gunrock 2.0: A User Adaptive Social Conversational Systemcited by 10

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 11; 2023: 14; 2024: 3; 2025: 3.

35 papers.

Sort:

By area:

  1. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  2. 2022Controllable Dialogue Simulation with In-Context Learningcited by 42
  3. 2023SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Promptingcited by 39
  4. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  5. 2021An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labelingcited by 26
  6. 2023Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Informationcited by 24
  7. 2022Decomposed Meta-Learning for Few-Shot Named Entity Recognitioncited by 22
  8. 2023Exploring Zero and Few-shot Techniques for Intent Classificationcited by 21
  9. 2022Label Semantic Aware Pre-training for Few-shot Text Classificationcited by 18
  10. 2022Learning Dialogue Representations from Consecutive Utterancescited by 17
  11. 2022Unsupervised Slot Schema Induction for Task-oriented Dialogcited by 11
  12. 2024LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classificationcited by 10
23 more
  1. 2021An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Fillingcited by 9
  2. 2022Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detectioncited by 7
  3. 2022A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanismcited by 6
  4. 2023Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsingcited by 6
  5. 2022Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Taggingcited by 5
  6. 2022Knowledge-grounded Dialog State Trackingcited by 5
  7. 2023Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-trainingcited by 5
  8. 2023PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Searchcited by 4
  9. 2023Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purificationcited by 4
  10. 2024Controllable and Diverse Data Augmentation with Large Language Model for Low-Resource Open-Domain Dialogue Generationcited by 4
  11. 2025REIC: RAG-Enhanced Intent Classification at Scalecited by 3
  12. 2023Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labelscited by 2
  13. 2021Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRFcited by 1
  14. 2022A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Examplecited by 1
  15. 2023Low-Resource Compositional Semantic Parsing with Concept Pretrainingcited by 1
  16. 2023Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Inductioncited by 1
  17. 2023Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generationcited by 1
  18. 2023Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddingscited by 1
  19. 2023Unifying Token and Span Level Supervisions for Few-Shot Sequence Labelingcited by 1
  20. 2023Causal Interventions-based Few-Shot Named Entity Recognitioncited by 0
  21. 2024Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learningcited by 0
  22. 2025Intent Classification on Low-Resource Languages with Query Similarity Searchcited by 0
  23. 2025Multi-Intent Spoken Language Understanding: Methods, Trends, and Challengescited by 0