Integrating Multiplicative Features into Supervised Distributional Methods for Lexical Entailment

Tu Vu, Vered Shwartz


Abstract
Supervised distributional methods are applied successfully in lexical entailment, but recent work questioned whether these methods actually learn a relation between two words. Specifically, Levy et al. (2015) claimed that linear classifiers learn only separate properties of each word. We suggest a cheap and easy way to boost the performance of these methods by integrating multiplicative features into commonly used representations. We provide an extensive evaluation with different classifiers and evaluation setups, and suggest a suitable evaluation setup for the task, eliminating biases existing in previous ones.
Anthology ID:
S18-2020
Volume:
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
*SEMEVAL
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
160–166
Language:
URL:
https://www.aclweb.org/anthology/S18-2020
DOI:
10.18653/v1/S18-2020
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/S18-2020.pdf