When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models

TL;DR

This paper improves hypernymy detection by combining pattern-based and distributional models, addressing their individual limitations and demonstrating enhanced performance and interpretability on benchmark datasets.

Contribution

It introduces a complementary framework that integrates pattern-based and distributional methods for hypernymy detection, especially in sparsity cases.

Findings

The framework achieves competitive improvements on benchmark datasets.

Distributional methods effectively complement pattern-based approaches in sparsity cases.

The combined approach offers better interpretability of hypernymy detection results.

Abstract

We address hypernymy detection, i.e., whether an is-a relationship exists between words (x, y), with the help of large textual corpora. Most conventional approaches to this task have been categorized to be either pattern-based or distributional. Recent studies suggest that pattern-based ones are superior, if large-scale Hearst pairs are extracted and fed, with the sparsity of unseen (x, y) pairs relieved. However, they become invalid in some specific sparsity cases, where x or y is not involved in any pattern. For the first time, this paper quantifies the non-negligible existence of those specific cases. We also demonstrate that distributional methods are ideal to make up for pattern-based ones in such cases. We devise a complementary framework, under which a pattern-based and a distributional model collaborate seamlessly in cases which they each prefer. On several benchmark datasets, our framework achieves competitive improvements and the case study shows its better interpretability.