SUNNYNLP at SemEval-2018 Task 10: A Support-Vector-Machine-Based Method for Detecting Semantic Difference using Taxonomy and Word Embedding Features

Sunny Lai, Kwong Sak Leung, Yee Leung


Abstract
We present SUNNYNLP, our system for solving SemEval 2018 Task 10: “Capturing Discriminative Attributes”. Our Support-Vector-Machine(SVM)-based system combines features extracted from pre-trained embeddings and statistical information from Is-A taxonomy to detect semantic difference of concepts pairs. Our system is demonstrated to be effective in detecting semantic difference and is ranked 1st in the competition in terms of F1 measure. The open source of our code is coined SUNNYNLP.
Anthology ID:
S18-1118
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:
741–746
Language:
URL:
https://www.aclweb.org/anthology/S18-1118
DOI:
10.18653/v1/S18-1118
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/S18-1118.pdf