Negative Sampling Improves Hypernymy Extraction Based on Projection Learning

TL;DR

This paper introduces a projection learning method with negative sampling for hypernym extraction, demonstrating significant performance improvements over previous classification-based approaches across multiple languages.

Contribution

It is the first to systematically study the impact of negative examples in hypernym prediction using projection learning.

Findings

Negative sampling improves hypernym extraction accuracy

The approach outperforms previous state-of-the-art methods

Effective across multiple languages

Abstract

We present a new approach to extraction of hypernyms based on projection learning and word embeddings. In contrast to classification-based approaches, projection-based methods require no candidate hyponym-hypernym pairs. While it is natural to use both positive and negative training examples in supervised relation extraction, the impact of negative examples on hypernym prediction was not studied so far. In this paper, we show that explicit negative examples used for regularization of the model significantly improve performance compared to the state-of-the-art approach of Fu et al. (2014) on three datasets from different languages.