{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/negative-sampling-improves-hypernymy","title":"Negative Sampling Improves Hypernymy Extraction Based on Projection Learning","arxiv_id":"1707.03903","date":"2017-07-12","proceeding":"EACL 2017 4","authors":["Dmitry Ustalov","Nikolay Arefyev","Chris Biemann","Alexander Panchenko"],"abstract":"We present a new approach to extraction of hypernyms based on projection\nlearning and word embeddings. In contrast to classification-based approaches,\nprojection-based methods require no candidate hyponym-hypernym pairs. While it\nis natural to use both positive and negative training examples in supervised\nrelation extraction, the impact of negative examples on hypernym prediction was\nnot studied so far. In this paper, we show that explicit negative examples used\nfor regularization of the model significantly improve performance compared to\nthe state-of-the-art approach of Fu et al. (2014) on three datasets from\ndifferent languages.","url_abs":"http://arxiv.org/abs/1707.03903v2","url_pdf":"http://arxiv.org/pdf/1707.03903v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"negative-sampling-improves-hypernymy","repo_url":"https://github.com/nlpub/projlearn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.03903","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}