Abstract
Cross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision. Simple ‘direct transfer’ of a learned model based on a multilingual input encoding has provided a strong benchmark. This paper presents a method for unsupervised cross-lingual transfer that improves over direct transfer systems by using their output as implicit supervision as part of self-training on unlabelled text in the target language. The method assumes minimal resources and provides maximal flexibility by (a) accepting any pre-trained arc-factored dependency parser; (b) assuming no access to source language data; (c) supporting both projective and non-projective parsing; and (d) supporting multi-source transfer. With English as the source language, we show significant improvements over state-of-the-art transfer models on both distant and nearby languages, despite our conceptually simpler approach. We provide analyses of the choice of source languages for multi-source transfer, and the advantage of non-projective parsing. Our code is available online.- Anthology ID:
- 2021.eacl-main.254
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2907–2918
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.254
- DOI:
- 10.18653/v1/2021.eacl-main.254
- Cite (ACL):
- Kemal Kurniawan, Lea Frermann, Philip Schulz, and Trevor Cohn. 2021. PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2907–2918, Online. Association for Computational Linguistics.
- Cite (Informal):
- PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation (Kurniawan et al., EACL 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2021.eacl-main.254.pdf
- Code
- kmkurn/ppt-eacl2021
- Data
- Universal Dependencies