MELA: Multilingual Evaluation of Linguistic Acceptability

Ziyin Zhang, Yikang Liu, Weifang Huang, Junyu Mao, Rui Wang, Hai Hu


Abstract
In this work, we present the largest benchmark to date on linguistic acceptability: Multilingual Evaluation of Linguistic Acceptability—MELA, with 46K samples covering 10 languages from a diverse set of language families. We establish LLM baselines on this benchmark, and investigate cross-lingual transfer in acceptability judgements with XLM-R. In pursuit of multilingual interpretability, we conduct probing experiments with fine-tuned XLM-R to explore the process of syntax capability acquisition. Our results show that GPT-4o exhibits a strong multilingual ability, outperforming fine-tuned XLM-R, while open-source multilingual models lag behind by a noticeable gap. Cross-lingual transfer experiments show that transfer in acceptability judgment is non-trivial: 500 Icelandic fine-tuning examples lead to 23 MCC performance in a completely unrelated language—Chinese. Results of our probing experiments indicate that training on MELA improves the performance of XLM-R on syntax-related tasks.
Anthology ID:
2024.acl-long.146
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2658–2674
Language:
URL:
https://aclanthology.org/2024.acl-long.146
DOI:
Bibkey:
Cite (ACL):
Ziyin Zhang, Yikang Liu, Weifang Huang, Junyu Mao, Rui Wang, and Hai Hu. 2024. MELA: Multilingual Evaluation of Linguistic Acceptability. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2658–2674, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
MELA: Multilingual Evaluation of Linguistic Acceptability (Zhang et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.acl-long.146.pdf