Abstract
We investigate the effect of various dependency-based word embeddings on distinguishing between functional and domain similarity, word similarity rankings, and two downstream tasks in English. Variations include word embeddings trained using context windows from Stanford and Universal dependencies at several levels of enhancement (ranging from unlabeled, to Enhanced++ dependencies). Results are compared to basic linear contexts and evaluated on several datasets. We found that embeddings trained with Universal and Stanford dependency contexts excel at different tasks, and that enhanced dependencies often improve performance.- Anthology ID:
- N18-4006
- Volume:
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana, USA
- Editors:
- Silvio Ricardo Cordeiro, Shereen Oraby, Umashanthi Pavalanathan, Kyeongmin Rim
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 40–45
- Language:
- URL:
- https://aclanthology.org/N18-4006
- DOI:
- 10.18653/v1/N18-4006
- Cite (ACL):
- Sean MacAvaney and Amir Zeldes. 2018. A Deeper Look into Dependency-Based Word Embeddings. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 40–45, New Orleans, Louisiana, USA. Association for Computational Linguistics.
- Cite (Informal):
- A Deeper Look into Dependency-Based Word Embeddings (MacAvaney & Zeldes, NAACL 2018)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/N18-4006.pdf
- Data
- Universal Dependencies