{"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/word2vec-explained-deriving-mikolov-et-als","title":"word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method","arxiv_id":"1402.3722","date":"2014-02-15","proceeding":null,"authors":["Yoav Goldberg","Omer Levy"],"abstract":"The word2vec software of Tomas Mikolov and colleagues\n(https://code.google.com/p/word2vec/ ) has gained a lot of traction lately, and\nprovides state-of-the-art word embeddings. The learning models behind the\nsoftware are described in two research papers. We found the description of the\nmodels in these papers to be somewhat cryptic and hard to follow. While the\nmotivations and presentation may be obvious to the neural-networks\nlanguage-modeling crowd, we had to struggle quite a bit to figure out the\nrationale behind the equations.\n  This note is an attempt to explain equation (4) (negative sampling) in\n\"Distributed Representations of Words and Phrases and their Compositionality\"\nby Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado and Jeffrey Dean.","url_abs":"http://arxiv.org/abs/1402.3722v1","url_pdf":"http://arxiv.org/pdf/1402.3722v1.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":"word2vec-explained-deriving-mikolov-et-als","repo_url":"https://github.com/123wowow123/chronopin","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"word2vec-explained-deriving-mikolov-et-als","repo_url":"https://github.com/LAEarnsChamp/skipgram-negativesampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"word2vec-explained-deriving-mikolov-et-als","repo_url":"https://github.com/LouisTernon/NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"word2vec-explained-deriving-mikolov-et-als","repo_url":"https://github.com/MLBurnham/word_embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"word2vec-explained-deriving-mikolov-et-als","repo_url":"https://github.com/devraj89/Deep-Learning-Resources","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1402.3722","atlas_url":"https://app.syntology.ai/?focus=1402.3722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1402.3722"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LAEarnsChamp/skipgram-negativesampling","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/123wowow123/chronopin","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LouisTernon/NLP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/devraj89/Deep-Learning-Resources","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MLBurnham/word_embeddings","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"24b8995c9efdcdb7","entry":"loadPairs","repo":"LouisTernon/NLP","repo_kind":"listed","path":"skipGram.py","file_url":"https://github.com/LouisTernon/NLP/blob/HEAD/skipGram.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24b8995c9efdcdb7"}},{"code_sha256_prefix":"375693019fa03226","entry":"text2sentences","repo":"LouisTernon/NLP","repo_kind":"listed","path":"skipGram.py","file_url":"https://github.com/LouisTernon/NLP/blob/HEAD/skipGram.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"375693019fa03226"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}