{"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/ultradense-word-embeddings-by-orthogonal","title":"Ultradense Word Embeddings by Orthogonal Transformation","arxiv_id":"1602.07572","date":"2016-02-24","proceeding":"NAACL 2016 6","authors":["Sascha Rothe","Sebastian Ebert","Hinrich Schütze"],"abstract":"Embeddings are generic representations that are useful for many NLP tasks. In\nthis paper, we introduce DENSIFIER, a method that learns an orthogonal\ntransformation of the embedding space that focuses the information relevant for\na task in an ultradense subspace of a dimensionality that is smaller by a\nfactor of 100 than the original space. We show that ultradense embeddings\ngenerated by DENSIFIER reach state of the art on a lexicon creation task in\nwhich words are annotated with three types of lexical information - sentiment,\nconcreteness and frequency. On the SemEval2015 10B sentiment analysis task we\nshow that no information is lost when the ultradense subspace is used, but\ntraining is an order of magnitude more efficient due to the compactness of the\nultradense space.","url_abs":"http://arxiv.org/abs/1602.07572v2","url_pdf":"http://arxiv.org/pdf/1602.07572v2.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":"ultradense-word-embeddings-by-orthogonal","repo_url":"https://github.com/pdufter/densray","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1602.07572","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}