mlsanityData to 14 Oct 2026

Cross-lingual Adaption Model-Agnostic Meta-Learning for Natural Language Understanding

arXiv 2111.05805 ↗First posted 10 Nov 2021cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Meta learning with auxiliary languages has demonstrated promising improvements for cross-lingual natural language processing. However, previous studies sample the meta-training and meta-testing data from the same language, which limits the ability of the model for cross-lingual transfer. In this paper, we propose XLA-MAML, which performs direct cross-lingual adaption in the meta-learning stage. We conduct zero-shot and few-shot experiments on Natural Language Inference and Question Answering. The experimental results demonstrate the effectiveness of our method across different languages, tasks, and pretrained models. We also give analysis on various cross-lingual specific settings for meta-learning including sampling strategy and parallelism.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 37 references that are in the map. First posted on arXiv 10 Nov 2021.

Builds on

31 of 37 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  6. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  9. 2016Matching Networks for One Shot Learningcited by 2,255
  10. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  11. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  12. 2019Cross-lingual Language Model Pretrainingcited by 1,090
19 more
  1. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  2. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 915
  3. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 742
  4. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 578
  5. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 488
  6. 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
  7. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  8. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 340
  9. 2019Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTcited by 301
  10. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 273
  11. 2017Meta Networkscited by 269
  12. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  13. 2020XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generationcited by 222
  14. 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
  15. 2019Generalized Inner Loop Meta-Learningcited by 93
  16. 2020Zero-Shot Cross-Lingual Transfer with Meta Learningcited by 66
  17. 2018Diverse Few-Shot Text Classification with Multiple Metricscited by 61
  18. 2019Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Taskscited by 48
  19. 2018Neural Cross-Lingual Named Entity Recognition with Minimal Resourcescited by 44

Built on by

Not cited yet.