Unsupervised Sense-Aware Hypernymy Extraction

TL;DR

This paper introduces an unsupervised method leveraging sense representations to improve hypernymy extraction by disambiguating relationships and propagating hypernyms across synsets, outperforming traditional pattern-based approaches.

Contribution

It presents a novel unsupervised approach for sense-aware hypernymy extraction that constructs embeddings for synsets and identifies disambiguated hypernymy relationships.

Findings

Successfully recognizes hypernymy relationships beyond Hearst patterns

Outperforms standard datasets in English and Russian

Effectively propagates hypernyms across synsets

Abstract

In this paper, we show how unsupervised sense representations can be used to improve hypernymy extraction. We present a method for extracting disambiguated hypernymy relationships that propagates hypernyms to sets of synonyms (synsets), constructs embeddings for these sets, and establishes sense-aware relationships between matching synsets. Evaluation on two gold standard datasets for English and Russian shows that the method successfully recognizes hypernymy relationships that cannot be found with standard Hearst patterns and Wiktionary datasets for the respective languages.