mlsanityData to 7 Oct 2026

Efficient Intent Detection with Dual Sentence Encoders

arXiv 2003.04807 ↗First posted 10 Mar 2020cs.CLcited by 419

Not on the map. Why?

Abstract (arXiv)

Building conversational systems in new domains and with added functionality requires resource-efficient models that work under low-data regimes (i.e., in few-shot setups). Motivated by these requirements, we introduce intent detection methods backed by pretrained dual sentence encoders such as USE and ConveRT. We demonstrate the usefulness and wide applicability of the proposed intent detectors, showing that: 1) they outperform intent detectors based on fine-tuning the full BERT-Large model or using BERT as a fixed black-box encoder on three diverse intent detection data sets; 2) the gains are especially pronounced in few-shot setups (i.e., with only 10 or 30 annotated examples per intent); 3) our intent detectors can be trained in a matter of minutes on a single CPU; and 4) they are stable across different hyperparameter settings. In hope of facilitating and democratizing research focused on intention detection, we release our code, as well as a new challenging single-domain intent detection dataset comprising 13,083 annotated examples over 77 intents.

Key facts. Cited by 419 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 50; 2023: 76; 2024: 93; 2025: 88; 2026: 84.

419 papers.

Sort:

By area:

  1. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  2. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 466
  3. 2024Jamba: A Hybrid Transformer-Mamba Language Modelcited by 390
  4. 2024Long-context LLMs Struggle with Long In-context Learningcited by 285
  5. 2026Meta-Harness: End-to-End Optimization of Model Harnessescited by 248
  6. 2024On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Surveycited by 240
  7. 2021PTR: Prompt Tuning with Rules for Text Classificationcited by 238
  8. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 236
  9. 2021ExT5: Towards Extreme Multi-Task Scaling for Transfer Learningcited by 161
  10. 2024How to Train Long-Context Language Models (Effectively)cited by 141
  11. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  12. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
38 more
  1. 2024In-Context Learning with Long-Context Models: An In-Depth Explorationcited by 126
  2. 2024HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughlycited by 119
  3. 2024Stable LM 2 1.6B Technical Reportcited by 86
  4. 2024Long-Context Language Modeling with Parallel Context Encodingcited by 84
  5. 2022Parallel Context Windows for Large Language Modelscited by 81
  6. 2024Making Text Embedders Few-Shot Learnerscited by 78
  7. 2024A Survey of Large Language Models in Finance (FinLLMs)cited by 77
  8. 2023Large Language Models Enable Few-Shot Clusteringcited by 72
  9. 2023ClusterLLM: Large Language Models as a Guide for Text Clusteringcited by 69
  10. 2021Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Wordscited by 63
  11. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 60
  12. 2022Data Augmentation for Intent Classification with Off-the-shelf Large Language Modelscited by 49
  13. 2025Mem-α: Learning Memory Construction via Reinforcement Learningcited by 49
  14. 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
  15. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  16. 2021RAFT: A Real-World Few-Shot Text Classification Benchmarkcited by 44
  17. 2021Out-of-Scope Intent Detection with Self-Supervision and Discriminative Trainingcited by 42
  18. 2022MIntRec: A New Dataset for Multimodal Intent Recognitioncited by 41
  19. 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
  20. 2021Improved Text Classification via Contrastive Adversarial Trainingcited by 38
  21. 2023Making LLMs Worth Every Penny: Resource-Limited Text Classification in Bankingcited by 36
  22. 2021Multilingual and Cross-Lingual Intent Detection from Spoken Datacited by 35
  23. 2022Generalized Category Discovery with Decoupled Prototypical Networkcited by 35
  24. 2023In-Context Learning for Text Classification with Many Labelscited by 35
  25. 2025KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Modelcited by 35
  26. 2021Efficient Domain Adaptation of Language Models via Adaptive Tokenizationcited by 34
  27. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  28. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  29. 2024A Survey on Data Augmentation in Large Model Eracited by 31
  30. 2021Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and Systemcited by 30
  31. 2023Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue Systemcited by 30
  32. 2023Split-and-Denoise: Protect large language model inference with local differential privacycited by 30
  33. 2024Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challengescited by 30
  34. 2024Serial Position Effects of Large Language Modelscited by 30
  35. 2022New Intent Discovery with Pre-training and Contrastive Learningcited by 28
  36. 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
  37. 2021Effectiveness of Pre-training for Few-shot Intent Classificationcited by 27
  38. 2023Primacy Effect of ChatGPTcited by 27

50 most cited of 419 All 419 (JSON)