Hypernyms Through Intra-Article Organization in Wikipedia

TL;DR

This paper proposes a lightweight, unsupervised method for hypernym detection and directionality using intra-article organization in Wikipedia, leveraging relative word positions and section titles.

Contribution

It introduces a novel, computationally simple measure based on article structure and section titles for hypernym detection, applicable across languages.

Findings

Achieves results comparable to state-of-the-art unsupervised methods

Uses relative physical location of words in articles

Utilizes section titles for semantic similarity

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.