mlsanityData to 14 Oct 2026

Nearest Neighbour Few-Shot Learning for Cross-lingual Classification

arXiv 2109.02221 ↗First posted 6 Sep 2021cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Even though large pre-trained multilingual models (e.g. mBERT, XLM-R) have led to significant performance gains on a wide range of cross-lingual NLP tasks, success on many downstream tasks still relies on the availability of sufficient annotated data. Traditional fine-tuning of pre-trained models using only a few target samples can cause over-fitting. This can be quite limiting as most languages in the world are under-resourced. In this work, we investigate cross-lingual adaptation using a simple nearest neighbor few-shot (<15 samples) inference technique for classification tasks. We experiment using a total of 16 distinct languages across two NLP tasks- XNLI and PAWS-X. Our approach consistently improves traditional fine-tuning using only a handful of labeled samples in target locales. We also demonstrate its generalization capability across tasks.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 37 of its 45 references that are in the map. First posted on arXiv 6 Sep 2021.

Builds on

37 of 45 references.

References · 37

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  7. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  8. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 915
  9. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  10. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  11. 2019How multilingual is Multilingual BERT?cited by 645
  12. 2020MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfercited by 445
25 more
  1. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 402
  2. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 370
  3. 2017A simple neural network module for relational reasoningcited by 346
  4. 2019Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTcited by 301
  5. 2020InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Trainingcited by 237
  6. 2020Nearest Neighbor Machine Translationcited by 209
  7. 2019Cross-Lingual Ability of Multilingual BERT: An Empirical Studycited by 182
  8. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  9. 2019Prototype Rectification for Few-Shot Learningcited by 97
  10. 2020Self-training Improves Pre-training for Natural Language Understandingcited by 96
  11. 2020Laplacian Regularized Few-Shot Learningcited by 92
  12. 2020Zero-Shot Cross-Lingual Transfer with Meta Learningcited by 66
  13. 2018Neural Cross-Lingual Named Entity Recognition with Minimal Resourcescited by 44
  14. 2020Paraphrase Augmented Task-Oriented Dialog Generationcited by 43
  15. 2020From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformerscited by 35
  16. 2020FILTER: An Enhanced Fusion Method for Cross-lingual Language Understandingcited by 29
  17. 2019Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NERcited by 25
  18. 2020LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Spacecited by 23
  19. 2020WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarizationcited by 23
  20. 2019Zero-Resource Cross-Lingual Named Entity Recognitioncited by 18
  21. 2020UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resource Cross-Lingual NLPcited by 14
  22. 2019Data Diversification: A Simple Strategy For Neural Machine Translationcited by 6
  23. 2017k-Nearest Neighbor Augmented Neural Networks for Text Classificationcited by 4
  24. 2021AUGVIC: Exploiting BiText Vicinity for Low-Resource NMTcited by 4
  25. 2020Continual Local Replacement for Few-shot Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 3; 2025: 2.

8 papers.

  1. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 98
  2. 2024REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environmentscited by 16
  3. 2024MINERS: Multilingual Language Models as Semantic Retrieverscited by 11
  4. 2024Towards flexible perception with visual memorycited by 8
  5. 2022SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learningcited by 5
  6. 2023Federated Nearest Neighbor Machine Translationcited by 5
  7. 2025Intent Classification on Low-Resource Languages with Query Similarity Searchcited by 0
  8. 2025Separating Knowledge and Perception with Procedural Datacited by 0