{"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/embedding-lexical-features-via-low-rank","title":"Embedding Lexical Features via Low-Rank Tensors","arxiv_id":"1604.00461","date":"2016-04-02","proceeding":"NAACL 2016 6","authors":["Mo Yu","Mark Dredze","Raman Arora","Matthew Gormley"],"abstract":"Modern NLP models rely heavily on engineered features, which often combine\nword and contextual information into complex lexical features. Such combination\nresults in large numbers of features, which can lead to over-fitting. We\npresent a new model that represents complex lexical features---comprised of\nparts for words, contextual information and labels---in a tensor that captures\nconjunction information among these parts. We apply low-rank tensor\napproximations to the corresponding parameter tensors to reduce the parameter\nspace and improve prediction speed. Furthermore, we investigate two methods for\nhandling features that include $n$-grams of mixed lengths. Our model achieves\nstate-of-the-art results on tasks in relation extraction, PP-attachment, and\npreposition disambiguation.","url_abs":"http://arxiv.org/abs/1604.00461v1","url_pdf":"http://arxiv.org/pdf/1604.00461v1.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":"embedding-lexical-features-via-low-rank","repo_url":"https://github.com/Gorov/LowRankFCM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.00461","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}