mlsanityData to 7 Oct 2026

Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing

arXiv 2104.04736 ↗First posted 10 Apr 2021cs.CL cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the task of cross-lingual dependency parsing. We train our model on a diverse set of languages to learn a parameter initialization that can adapt quickly to new languages. We find that meta-learning with pre-training can significantly improve upon the performance of language transfer and standard supervised learning baselines for a variety of unseen, typologically diverse, and low-resource languages, in a few-shot learning setup.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 21 of its 42 references that are in the map. First posted on arXiv 10 Apr 2021.

Builds on

21 of 42 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  7. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
  8. 2019Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTcited by 301
  9. 201975 Languages, 1 Model: Parsing Universal Dependencies Universallycited by 90
  10. 2019Learning and Evaluating General Linguistic Intelligencecited by 78
  11. 2020UDapter: Language Adaptation for Truly Universal Dependency Parsingcited by 77
  12. 2019Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsingcited by 69
9 more
  1. 2020Zero-Shot Cross-Lingual Transfer with Meta Learningcited by 66
  2. 2020From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformerscited by 35
  3. 2018Natural Language to Structured Query Generation via Meta-Learningcited by 33
  4. 2016Many Languages, One Parsercited by 26
  5. 2019Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resourcescited by 25
  6. 2018Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenationcited by 21
  7. 2019Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence Representationscited by 17
  8. 2020Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguationcited by 13
  9. 2020Learning to Learn Morphological Inflection for Resource-Poor Languagescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 2; 2024: 4; 2025: 0; 2026: 1.

10 papers.

  1. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  2. 2024Enhancing Healthcare through Large Language Models: A Study on Medical Question Answeringcited by 14
  3. 2024The Zeno's Paradox of `Low-Resource' Languagescited by 12
  4. 2023Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalizationcited by 6
  5. 2022Data-Efficient Cross-Lingual Transfer with Language-Specific Subnetworkscited by 2
  6. 2024Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsingcited by 2
  7. 2023Multilingual Sentence-Level Semantic Search using Meta-Distillation Learningcited by 1
  8. 2024Incorporating Lexical and Syntactic Knowledge for Unsupervised Cross-Lingual Transfercited by 1
  9. 2022Learning New Tasks from a Few Examples with Soft-Label Prototypescited by 0
  10. 2026Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrappingcited by 0