mlsanityData to 14 Oct 2026

Few-shot learning for medical text: A systematic review

arXiv 2204.14081 ↗First posted 21 Apr 2022cs.CL cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Objective: Few-shot learning (FSL) methods require small numbers of labeled instances for training. As many medical topics have limited annotated textual data in practical settings, FSL-based natural language processing (NLP) methods hold substantial promise. We aimed to conduct a systematic review to explore the state of FSL methods for medical NLP. Materials and Methods: We searched for articles published between January 2016 and August 2021 using PubMed/Medline, Embase, ACL Anthology, and IEEE Xplore Digital Library. To identify the latest relevant methods, we also searched other sources such as preprint servers (eg., medRxiv) via Google Scholar. We included all articles that involved FSL and any type of medical text. We abstracted articles based on data source(s), aim(s), training set size(s), primary method(s)/approach(es), and evaluation method(s). Results: 31 studies met our inclusion criteria-all published after 2018; 22 (71%) since 2020. Concept extraction/named entity recognition was the most frequently addressed task (13/31; 42%), followed by text classification (10/31; 32%). Twenty-one (68%) studies reconstructed existing datasets to create few-shot scenarios synthetically, and MIMIC-III was the most frequently used dataset (7/31; 23%). Common methods included FSL with attention mechanisms (12/31; 39%), prototypical networks (8/31; 26%), and meta-learning (6/31; 19%). Discussion: Despite the potential for FSL in biomedical NLP, progress has been limited compared to domain-independent FSL. This may be due to the paucity of standardized, public datasets, and the relative underperformance of FSL methods on biomedical topics. Creation and release of specialized datasets for biomedical FSL may aid method development by enabling comparative analyses.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 31 of its 97 references that are in the map. First posted on arXiv 21 Apr 2022.

Builds on

31 of 97 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  8. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  9. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  10. 2021A Survey of Data Augmentation Approaches for NLPcited by 409
  11. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  12. 2017Recent Trends in Deep Learning Based Natural Language Processingcited by 263
19 more
  1. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  2. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  3. 2019Large-Scale Multi-Label Text Classification on EU Legislationcited by 104
  4. 2019FewRel 2.0: Towards More Challenging Few-Shot Relation Classificationcited by 94
  5. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  6. 2019Induction Networks for Few-Shot Text Classificationcited by 64
  7. 2021Towards Few-Shot Fact-Checking via Perplexitycited by 63
  8. 2019Few-Shot NLG with Pre-Trained Language Modelcited by 52
  9. 2020An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labelscited by 44
  10. 2020Few-Shot Named Entity Recognition: A Comprehensive Studycited by 41
  11. 2017Learning Algorithms for Active Learningcited by 30
  12. 2016Learning Reporting Dynamics during Breaking News for Rumour Detection in Social Mediacited by 25
  13. 2020Meta-Learning for Few-Shot NMT Adaptationcited by 20
  14. 2018Few-shot Learning for Named Entity Recognition in Medical Textcited by 19
  15. 2020Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphscited by 19
  16. 2020Med7: a transferable clinical natural language processing model for electronic health recordscited by 15
  17. 2018Towards one-shot learning for rare-word translation with external expertscited by 10
  18. 2020FewJoint: A Few-shot Learning Benchmark for Joint Language Understandingcited by 10
  19. 2020NUBES: A Corpus of Negation and Uncertainty in Spanish Clinical Textscited by 4

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 7.

13 papers.

Sort:

By area:

  1. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 130
  2. 2024Language Models for Text Classification: Is In-Context Learning Enough?cited by 40
  3. 2023Mask-guided BERT for Few Shot Text Classificationcited by 25
  4. 2024MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Modelscited by 15
  5. 2023Enhancing Small Medical Learners with Privacy-preserving Contextual Promptingcited by 11
  6. 2024Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learningcited by 10
  7. 2023Few Shot Learning for Medical Imaging: A Comparative Analysis of Methodologies and Formal Mathematical Frameworkcited by 9
  8. 2024ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Taskscited by 8
  9. 2024A Survey of Few-Shot Learning for Biomedical Time Seriescited by 7
  10. 2024FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Modelscited by 3
  11. 2022Few-Shot Learning for Clinical Natural Language Processing Using Siamese Neural Networkscited by 1
  12. 2024Extracting Biomedical Entities from Noisy Audio Transcriptscited by 1
1 more
  1. 2022Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networkscited by 0