Spot the Odd Man Out: Exploring the Associative Power of Lexical Resources

Gabriel Stanovsky, Mark Hopkins


Abstract
We propose Odd-Man-Out, a novel task which aims to test different properties of word representations. An Odd-Man-Out puzzle is composed of 5 (or more) words, and requires the system to choose the one which does not belong with the others. We show that this simple setup is capable of teasing out various properties of different popular lexical resources (like WordNet and pre-trained word embeddings), while being intuitive enough to annotate on a large scale. In addition, we propose a novel technique for training multi-prototype word representations, based on unsupervised clustering of ELMo embeddings, and show that it surpasses all other representations on all Odd-Man-Out collections.
Anthology ID:
D18-1182
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1533–1542
Language:
URL:
https://www.aclweb.org/anthology/D18-1182
DOI:
10.18653/v1/D18-1182
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D18-1182.pdf