Hypernyms Through Intra-Article Organization in Wikipedia
Information Retrieval
2018-09-05 v1 Artificial Intelligence
Computation and Language
Machine Learning
Abstract
We introduce a new measure for unsupervised hypernym detection and directionality. The motivation is to keep the measure computationally light and portatable across languages. We show that the relative physical location of words in explanatory articles captures the directionality property. Further, the phrases in section titles of articles about the word, capture the semantic similarity needed for hypernym detection task. We experimentally show that the combination of features coming from these two simple measures suffices to produce results comparable with the best unsupervised measures in terms of the average precision.
Cite
@article{arxiv.1809.00414,
title = {Hypernyms Through Intra-Article Organization in Wikipedia},
author = {Disha Shrivastava and Sreyash Kenkre and Santosh Penubothula},
journal= {arXiv preprint arXiv:1809.00414},
year = {2018}
}