تقرير
Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing
العنوان: | Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing |
---|---|
المؤلفون: | Langedijk, Anna, Dankers, Verna, Lippe, Phillip, Bos, Sander, Guevara, Bryan Cardenas, Yannakoudakis, Helen, Shutova, Ekaterina |
سنة النشر: | 2021 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
الوصف: | 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. Comment: - Add additional results (Appendix D) - Cosmetic updates for camera-ready version ACL 2022 |
نوع الوثيقة: | Working Paper |
الوصول الحر: | http://arxiv.org/abs/2104.04736Test |
رقم الانضمام: | edsarx.2104.04736 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |