UMD at SemEval-2018 Task 10: Can Word Embeddings Capture Discriminative Attributes?

Alexander Zhang, Marine Carpuat


Abstract
We describe the University of Maryland’s submission to SemEval-018 Task 10, “Capturing Discriminative Attributes”: given word triples (w1, w2, d), the goal is to determine whether d is a discriminating attribute belonging to w1 but not w2. Our study aims to determine whether word embeddings can address this challenging task. Our submission casts this problem as supervised binary classification using only word embedding features. Using a gaussian SVM model trained only on validation data results in an F-score of 60%. We also show that cosine similarity features are more effective, both in unsupervised systems (F-score of 65%) and supervised systems (F-score of 67%).
Anthology ID:
S18-1170
Volume:
Proceedings of The 12th International Workshop on Semantic Evaluation
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
*SEMEVAL
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
1022–1026
Language:
URL:
https://www.aclweb.org/anthology/S18-1170
DOI:
10.18653/v1/S18-1170
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/S18-1170.pdf