{"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/subgram-extending-skip-gram-word","title":"SubGram: Extending Skip-gram Word Representation with Substrings","arxiv_id":"1806.06571","date":"2018-06-18","proceeding":null,"authors":["Tom Kocmi","Ondřej Bojar"],"abstract":"Skip-gram (word2vec) is a recent method for creating vector representations\nof words (\"distributed word representations\") using a neural network. The\nrepresentation gained popularity in various areas of natural language\nprocessing, because it seems to capture syntactic and semantic information\nabout words without any explicit supervision in this respect. We propose\nSubGram, a refinement of the Skip-gram model to consider also the word\nstructure during the training process, achieving large gains on the Skip-gram\noriginal test set.","url_abs":"http://arxiv.org/abs/1806.06571v1","url_pdf":"http://arxiv.org/pdf/1806.06571v1.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":"subgram-extending-skip-gram-word","repo_url":"https://github.com/tomkocmi/SubGram","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}