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.
@article{arxiv.1707.03903,
title = {Negative Sampling Improves Hypernymy Extraction Based on Projection Learning},
author = {Dmitry Ustalov and Nikolay Arefyev and Chris Biemann and Alexander Panchenko},
journal= {arXiv preprint arXiv:1707.03903},
year = {2018}
}
Comments
In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL'2017). Valencia, Spain. Association for Computational Linguistics