Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks
Şaziye Betül Özateş, Arzucan Özgür, Tunga Gungor, Özlem Çetinoğlu
Abstract
Code-switching dependency parsing stands as a challenging task due to both the scarcity of necessary resources and the structural difficulties embedded in code-switched languages. In this study, we introduce novel sequence labeling models to be used as auxiliary tasks for dependency parsing of code-switched text in a semi-supervised scheme. We show that using auxiliary tasks enhances the performance of an LSTM-based dependency parsing model and leads to better results compared to an XLM-R-based model with significantly less computational and time complexity. As the first study that focuses on multiple code-switching language pairs for dependency parsing, we acquire state-of-the-art scores on all of the studied languages. Our best models outperform the previous work by 7.4 LAS points on average.- Anthology ID:
- 2022.findings-naacl.87
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2022
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1159–1171
- Language:
- URL:
- https://aclanthology.org/2022.findings-naacl.87
- DOI:
- 10.18653/v1/2022.findings-naacl.87
- Cite (ACL):
- Şaziye Betül Özateş, Arzucan Özgür, Tunga Gungor, and Özlem Çetinoğlu. 2022. Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1159–1171, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks (Özateş et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2022.findings-naacl.87.pdf
- Code
- sb-b/ss-cs-depparser
- Data
- LinCE, Universal Dependencies