Abstract
Languages evolve and diverge over time. Their evolutionary history is often depicted in the shape of a phylogenetic tree. Assuming parsing models are representations of their languages grammars, their evolution should follow a structure similar to that of the phylogenetic tree. In this paper, drawing inspiration from multi-task learning, we make use of the phylogenetic tree to guide the learning of multi-lingual dependency parsers leveraging languages structural similarities. Experiments on data from the Universal Dependency project show that phylogenetic training is beneficial to low resourced languages and to well furnished languages families. As a side product of phylogenetic training, our model is able to perform zero-shot parsing of previously unseen languages.- Anthology ID:
- N19-1017
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 192–203
- Language:
- URL:
- https://aclanthology.org/N19-1017
- DOI:
- 10.18653/v1/N19-1017
- Cite (ACL):
- Mathieu Dehouck and Pascal Denis. 2019. Phylogenic Multi-Lingual Dependency Parsing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 192–203, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Phylogenic Multi-Lingual Dependency Parsing (Dehouck & Denis, NAACL 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/N19-1017.pdf