Persian Natural Language Inference: A Meta-learning Approach

Heydar Soudani, Mohammad Hassan Mojab, Hamid Beigy


Abstract
Incorporating information from other languages can improve the results of tasks in low-resource languages. A powerful method of building functional natural language processing systems for low-resource languages is to combine multilingual pre-trained representations with cross-lingual transfer learning. In general, however, shared representations are learned separately, either across tasks or across languages. This paper proposes a meta-learning approach for inferring natural language in Persian. Alternately, meta-learning uses different task information (such as QA in Persian) or other language information (such as natural language inference in English). Also, we investigate the role of task augmentation strategy for forming additional high-quality tasks. We evaluate the proposed method using four languages and an auxiliary task. Compared to the baseline approach, the proposed model consistently outperforms it, improving accuracy by roughly six percent. We also examine the effect of finding appropriate initial parameters using zero-shot evaluation and CCA similarity.
Anthology ID:
2022.coling-1.380
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4306–4319
Language:
URL:
https://aclanthology.org/2022.coling-1.380
DOI:
Bibkey:
Cite (ACL):
Heydar Soudani, Mohammad Hassan Mojab, and Hamid Beigy. 2022. Persian Natural Language Inference: A Meta-learning Approach. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4306–4319, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Persian Natural Language Inference: A Meta-learning Approach (Soudani et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.380.pdf
Code
 hassanmojab/metanli
Data
FarsTailPersianQAXTREME