Abstract
In cross-lingual dependency annotation projection, information is often lost during transfer because of early decoding. We present an end-to-end graph-based neural network dependency parser that can be trained to reproduce matrices of edge scores, which can be directly projected across word alignments. We show that our approach to cross-lingual dependency parsing is not only simpler, but also achieves an absolute improvement of 2.25% averaged across 10 languages compared to the previous state of the art.- Anthology ID:
- E17-1021
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Editors:
- Mirella Lapata, Phil Blunsom, Alexander Koller
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 220–229
- Language:
- URL:
- https://aclanthology.org/E17-1021
- DOI:
- Cite (ACL):
- Michael Schlichtkrull and Anders Søgaard. 2017. Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 220–229, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages (Schlichtkrull & Søgaard, EACL 2017)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/E17-1021.pdf
- Code
- MichSchli/Tensor-LSTM