Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations
Abstract
Recognizing various semantic relations between terms is beneficial for many NLP tasks. While path-based and distributional information sources are considered complementary for this task, the superior results the latter showed recently suggested that the former's contribution might have become obsolete. We follow the recent success of an integrated neural method for hypernymy detection (Shwartz et al., 2016) and extend it to recognize multiple relations. The empirical results show that this method is effective in the multiclass setting as well. We further show that the path-based information source always contributes to the classification, and analyze the cases in which it mostly complements the distributional information.
Cite
@article{arxiv.1608.05014,
title = {Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations},
author = {Vered Shwartz and Ido Dagan},
journal= {arXiv preprint arXiv:1608.05014},
year = {2016}
}
Comments
5 pages, accepted to the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex-V), in COLING 2016