Zero-Shot Cross-Lingual Transfer with Meta Learning
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Zero-Shot Cross-Lingual Transfer with Meta Learning. / Nooralahzadeh, Farhad; Bekoulis, Giannis; Bjerva, Johannes; Augenstein, Isabelle.
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, 2020. p. 4547-4562.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Zero-Shot Cross-Lingual Transfer with Meta Learning
AU - Nooralahzadeh, Farhad
AU - Bekoulis, Giannis
AU - Bjerva, Johannes
AU - Augenstein, Isabelle
PY - 2020
Y1 - 2020
N2 - Learning what to share between tasks has become a topic of great importance, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as most languages in the world are under-resourced. Here, we consider the setting of training models on multiple different languages at the same time, when little or no data is available for languages other than English. We show that this challenging setup can be approached using meta-learning: in addition to training a source language model, another model learns to select which training instances are the most beneficial to the first. We experiment using standard supervised, zero-shot cross-lingual, as well as few-shot cross-lingual settings for different natural language understanding tasks (natural language inference, question answering). Our extensive experimental setup demonstrates the consistent effectiveness of meta-learning for a total of 15 languages. We improve upon the state-of-the-art for zero-shot and few-shot NLI (on MultiNLI and XNLI) and QA (on the MLQA dataset). A comprehensive error analysis indicates that the correlation of typological features between languages can partly explain when parameter sharing learned via meta-learning is beneficial.
AB - Learning what to share between tasks has become a topic of great importance, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as most languages in the world are under-resourced. Here, we consider the setting of training models on multiple different languages at the same time, when little or no data is available for languages other than English. We show that this challenging setup can be approached using meta-learning: in addition to training a source language model, another model learns to select which training instances are the most beneficial to the first. We experiment using standard supervised, zero-shot cross-lingual, as well as few-shot cross-lingual settings for different natural language understanding tasks (natural language inference, question answering). Our extensive experimental setup demonstrates the consistent effectiveness of meta-learning for a total of 15 languages. We improve upon the state-of-the-art for zero-shot and few-shot NLI (on MultiNLI and XNLI) and QA (on the MLQA dataset). A comprehensive error analysis indicates that the correlation of typological features between languages can partly explain when parameter sharing learned via meta-learning is beneficial.
U2 - 10.18653/v1/2020.emnlp-main.368
DO - 10.18653/v1/2020.emnlp-main.368
M3 - Article in proceedings
SP - 4547
EP - 4562
BT - Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
PB - Association for Computational Linguistics
T2 - The 2020 Conference on Empirical Methods in Natural Language Processing
Y2 - 16 November 2020 through 20 November 2020
ER -
ID: 254992325