Abstract
We use both Bayesian and neural models to dissect a data set of Chinese learners’ pre- and post-interventional responses to two tests measuring their understanding of English prepositions. The results mostly replicate previous findings from frequentist analyses and newly reveal crucial interactions between student ability, task type, and stimulus sentence. Given the sparsity of the data as well as high diversity among learners, the Bayesian method proves most useful; but we also see potential in using language model probabilities as predictors of grammaticality and learnability.- Anthology ID:
- 2023.acl-long.712
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12722–12736
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.712
- DOI:
- 10.18653/v1/2023.acl-long.712
- Cite (ACL):
- Jakob Prange and Man Ho Ivy Wong. 2023. Reanalyzing L2 Preposition Learning with Bayesian Mixed Effects and a Pretrained Language Model. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12722–12736, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Reanalyzing L2 Preposition Learning with Bayesian Mixed Effects and a Pretrained Language Model (Prange & Wong, ACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.acl-long.712.pdf