Negative Sampling Improves Hypernymy Extraction Based on Projection Learning

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.

In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL'2017). Valencia, Spain. Association for Computational Linguistics

References in corpus (2)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Human and Machine Judgements for Russian Semantic Relatedness

Cited by in corpus (5)

• When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models
• Creation and Evaluation of Datasets for Distributional Semantics Tasks in the Digital Humanities Domain
• Relation Extraction Datasets in the Digital Humanities Domain and their Evaluation with Word Embeddings
• Technological taxonomies for hypernym and hyponym retrieval in patent texts
• Unsupervised Sense-Aware Hypernymy Extraction