Abstract
This paper describes LIMSI’s submission to the CoNLL 2017 UD Shared Task, which is focused on small treebanks, and how to improve low-resourced parsing only by ad hoc combination of multiple views and resources. We present our approach for low-resourced parsing, together with a detailed analysis of the results for each test treebank. We also report extensive analysis experiments on model selection for the PUD treebanks, and on annotation consistency among UD treebanks.- Anthology ID:
- K17-3017
- Volume:
- Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
- Month:
- August
- Year:
- 2017
- Address:
- Vancouver, Canada
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 163–173
- Language:
- URL:
- https://aclanthology.org/K17-3017
- DOI:
- 10.18653/v1/K17-3017
- Cite (ACL):
- Lauriane Aufrant, Guillaume Wisniewski, and François Yvon. 2017. LIMSI@CoNLL’17: UD Shared Task. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 163–173, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- LIMSI@CoNLL’17: UD Shared Task (Aufrant et al., CoNLL 2017)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/K17-3017.pdf
- Data
- Universal Dependencies