mlsanityData to 7 Oct 2026

Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

arXiv 2104.11882 ↗First posted 24 Apr 2021cs.CLcited by 30

Not on the map. Why?

Abstract (arXiv)

Text classification is usually studied by labeling natural language texts with relevant categories from a predefined set. In the real world, new classes might keep challenging the existing system with limited labeled data. The system should be intelligent enough to recognize upcoming new classes with a few examples. In this work, we define a new task in the NLP domain, incremental few-shot text classification, where the system incrementally handles multiple rounds of new classes. For each round, there is a batch of new classes with a few labeled examples per class. Two major challenges exist in this new task: (i) For the learning process, the system should incrementally learn new classes round by round without re-training on the examples of preceding classes; (ii) For the performance, the system should perform well on new classes without much loss on preceding classes. In addition to formulating the new task, we also release two benchmark datasets in the incremental few-shot setting: intent classification and relation classification. Moreover, we propose two entailment approaches, ENTAILMENT and HYBRID, which show promise for solving this novel problem.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 21 of its 27 references that are in the map. First posted on arXiv 24 Apr 2021.

Builds on

21 of 27 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  5. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  6. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
  7. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  8. 2019Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approachcited by 299
  9. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  10. 2019Text Classification Algorithms: A Surveycited by 163
  11. 2016Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Fillingcited by 137
  12. 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 65
9 more
  1. 2019Induction Networks for Few-Shot Text Classificationcited by 64
  2. 2019SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominalscited by 63
  3. 2018Diverse Few-Shot Text Classification with Multiple Metricscited by 61
  4. 2018Zero-shot User Intent Detection via Capsule Neural Networkscited by 54
  5. 2020Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inferencecited by 47
  6. 2020Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Startcited by 44
  7. 2020CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detectioncited by 23
  8. 2020Composed Variational Natural Language Generation for Few-shot Intentscited by 19
  9. 2020Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detectioncited by 17

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 10; 2023: 6; 2024: 7; 2025: 3.

30 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2021Meta-learning via Language Model In-context Tuningcited by 163
  3. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  4. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 60
  5. 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
  6. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  7. 2022Memory Efficient Continual Learning with Transformerscited by 43
  8. 2022Continual Training of Language Models for Few-Shot Learningcited by 33
  9. 2021Unsupervised Out-of-Domain Detection via Pre-trained Transformerscited by 31
  10. 2023Large Language Model Instruction Following: A Survey of Progresses and Challengescited by 31
  11. 2022ConTinTin: Continual Learning from Task Instructionscited by 26
  12. 2022Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropizationcited by 19
18 more
  1. 2021Pseudo Siamese Network for Few-shot Intent Generationcited by 11
  2. 2024On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writingcited by 10
  3. 2023What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventoriescited by 9
  4. 2023Intent Identification and Entity Extraction for Healthcare Queries in Indic Languagescited by 9
  5. 2024Major Entity Identification: A Generalizable Alternative to Coreference Resolutioncited by 9
  6. 2022OpenStance: Real-world Zero-shot Stance Detectioncited by 7
  7. 2025AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMscited by 7
  8. 2024Intent Detection and Entity Extraction from BioMedical Literaturecited by 6
  9. 2025Text Takes Over: A Study of Modality Bias in Multimodal Intent Detectioncited by 6
  10. 2023Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-trainingcited by 5
  11. 2022Learning to Select from Multiple Optionscited by 4
  12. 2024Domain Adaptation in Intent Classification Systems: A Reviewcited by 4
  13. 2024A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intentscited by 3
  14. 2022A Framework to Generate High-Quality Datapoints for Multiple Novel Intent Detectioncited by 2
  15. 2023All Labels Together: Low-shot Intent Detection with an Efficient Label Semantic Encoding Paradigmcited by 1
  16. 2022Few-shot Incremental Event Detectioncited by 0
  17. 2022ConEntail: An Entailment-based Framework for Universal Zero and Few Shot Classification with Supervised Contrastive Pretrainingcited by 0
  18. 2025IDALC: A Semi-Supervised Framework for Intent Detection and Active Learning based Correctioncited by 0