Using dependency parsing for few-shot learning in distributional semantics

Stefania Preda, Guy Emerson


Abstract
In this work, we explore the novel idea of employing dependency parsing information in the context of few-shot learning, the task of learning the meaning of a rare word based on a limited amount of context sentences. Firstly, we use dependency-based word embedding models as background spaces for few-shot learning. Secondly, we introduce two few-shot learning methods which enhance the additive baseline model by using dependencies.
Anthology ID:
2022.acl-srw.38
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Samuel Louvan, Andrea Madotto, Brielen Madureira
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
461–466
Language:
URL:
https://aclanthology.org/2022.acl-srw.38
DOI:
10.18653/v1/2022.acl-srw.38
Bibkey:
Cite (ACL):
Stefania Preda and Guy Emerson. 2022. Using dependency parsing for few-shot learning in distributional semantics. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 461–466, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Using dependency parsing for few-shot learning in distributional semantics (Preda & Emerson, ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-srw.38.pdf