Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks
2022 Findings of the Association for Computational Linguistics: NAACL 2022, Washington, Amerika Birleşik Devletleri, 10 - 15 Temmuz 2022, ss.1159-1171, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.18653/v1/2022.findings-naacl.87
- Basıldığı Şehir: Washington
- Basıldığı Ülke: Amerika Birleşik Devletleri
- Sayfa Sayıları: ss.1159-1171
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Boğaziçi Üniversitesi Adresli: Evet
Özet
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-Rbased model with significantly less computational and space 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.