Abstract
This paper describes the neural dependency parser submitted by Stanford to the CoNLL 2017 Shared Task on parsing Universal Dependencies. Our system uses relatively simple LSTM networks to produce part of speech tags and labeled dependency parses from segmented and tokenized sequences of words. In order to address the rare word problem that abounds in languages with complex morphology, we include a character-based word representation that uses an LSTM to produce embeddings from sequences of characters. Our system was ranked first according to all five relevant metrics for the system: UPOS tagging (93.09%), XPOS tagging (82.27%), unlabeled attachment score (81.30%), labeled attachment score (76.30%), and content word labeled attachment score (72.57%).- Anthology ID:
- K17-3002
- 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:
- 20–30
- Language:
- URL:
- https://aclanthology.org/K17-3002
- DOI:
- 10.18653/v1/K17-3002
- Cite (ACL):
- Timothy Dozat, Peng Qi, and Christopher D. Manning. 2017. Stanford’s Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 20–30, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Stanford’s Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task (Dozat et al., CoNLL 2017)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/K17-3002.pdf
- Data
- Universal Dependencies