A Deeper Look into Dependency-Based Word Embeddings

Sean MacAvaney, Amir Zeldes


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
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
40–45
Language:
URL:
https://www.aclweb.org/anthology/N18-4006
DOI:
10.18653/v1/N18-4006
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N18-4006.pdf