Abstract
We describe our submission to the CoNLL 2017 shared task, which exploits the shared common knowledge of a language across different domains via a domain adaptation technique. Our approach is an extension to the recently proposed adversarial training technique for domain adaptation, which we apply on top of a graph-based neural dependency parsing model on bidirectional LSTMs. In our experiments, we find our baseline graph-based parser already outperforms the official baseline model (UDPipe) by a large margin. Further, by applying our technique to the treebanks of the same language with different domains, we observe an additional gain in the performance, in particular for the domains with less training data.- Anthology ID:
- K17-3007
- Volume:
- Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
- Month:
- August
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Jan Hajič, Dan Zeman
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 71–79
- Language:
- URL:
- https://aclanthology.org/K17-3007
- DOI:
- 10.18653/v1/K17-3007
- Cite (ACL):
- Motoki Sato, Hitoshi Manabe, Hiroshi Noji, and Yuji Matsumoto. 2017. Adversarial Training for Cross-Domain Universal Dependency Parsing. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 71–79, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Adversarial Training for Cross-Domain Universal Dependency Parsing (Sato et al., CoNLL 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/K17-3007.pdf