{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/skip-gram-word2vec","slug":"skip-gram-word2vec","name":"Skip-gram Word2Vec","full_name":"Skip-gram Word2Vec","full_name_withheld":false,"description_markdown":"**Skip-gram Word2Vec** is an architecture for computing word embeddings. Instead of using surrounding words to predict the center word, as with CBow Word2Vec, Skip-gram Word2Vec uses the central word to predict the surrounding words.\r\n\r\nThe skip-gram objective function sums the log probabilities of the surrounding $n$ words to the left and right of the target word $w\\_{t}$ to produce the following objective:\r\n\r\n$$J\\_\\theta = \\frac{1}{T}\\sum^{T}\\_{t=1}\\sum\\_{-n\\leq{j}\\leq{n}, \\neq{0}}\\log{p}\\left(w\\_{j+1}\\mid{w\\_{t}}\\right)$$","description_state":"present","introduced_year":null,"introduced_by":{"title":"Efficient Estimation of Word Representations in Vector Space","paper":"/paper/efficient-estimation-of-word-representations","first_author":"Tomas Mikolov","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/efficient-estimation-of-word-representations"},"source":{"url":"http://arxiv.org/abs/1301.3781v3","title":"Efficient Estimation of Word Representations in Vector Space","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Static Word Embeddings","url":"/methods/category/static-word-embeddings","pwc_aliases":[]},{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Word Embeddings","url":"/methods/category/word-embeddings","pwc_aliases":[]}],"n_papers_tagged":14,"archive_num_papers":14,"papers_newest_first":[{"paper":"/paper/rdf-star2vec-rdf-star-graph-embeddings-for","slug":"rdf-star2vec-rdf-star-graph-embeddings-for","title":"RDF-star2Vec: RDF-star Graph Embeddings for Data Mining","date":"2023-12-25","arxiv_id":"2312.15626","n_code_links":2,"syntology":null},{"paper":"/paper/evaluating-unsupervised-text-classification","slug":"evaluating-unsupervised-text-classification","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","date":"2022-11-29","arxiv_id":"2211.16285","n_code_links":2,"syntology":null},{"paper":null,"slug":"walk-this-way-entity-walks-and-property-walks","title":"Walk this Way! Entity Walks and Property Walks for RDF2vec","date":"2022-04-05","arxiv_id":"2204.02777","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-subword-guided-neural-word-segmentation","title":"Enhancing Sindhi Word Segmentation using Subword Representation Learning and Position-aware Self-attention","date":"2020-12-30","arxiv_id":"2012.15079","n_code_links":0,"syntology":null},{"paper":"/paper/improving-clinical-document-understanding-on","slug":"improving-clinical-document-understanding-on","title":"Improving Clinical Document Understanding on COVID-19 Research with Spark NLP","date":"2020-12-07","arxiv_id":"2012.04005","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-query-target-knowledge-discovery","title":"Transformer Query-Target Knowledge Discovery (TEND): Drug Discovery from CORD-19","date":"2020-11-28","arxiv_id":"2012.04682","n_code_links":0,"syntology":null},{"paper":"/paper/farstail-a-persian-natural-language-inference","slug":"farstail-a-persian-natural-language-inference","title":"FarsTail: A Persian Natural Language Inference Dataset","date":"2020-09-18","arxiv_id":"2009.08820","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpreting-pretrained-contextualized","title":"Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"why-is-penguin-more-similar-to-polar-bear","title":"Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/topic-modeling-in-embedding-spaces","slug":"topic-modeling-in-embedding-spaces","title":"Topic Modeling in Embedding Spaces","date":"2019-07-08","arxiv_id":"1907.04907","n_code_links":12,"syntology":{"ran":10,"of":13,"n_ran_checked":9,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["adjidieng/ETM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"an-empirical-evaluation-of-text","title":"An Empirical Evaluation of Text Representation Schemes on Multilingual Social Web to Filter the Textual Aggression","date":"2019-04-16","arxiv_id":"1904.08770","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-role-relevance-with-minimal-domain","title":"Predicting Role Relevance with Minimal Domain Expertise in a Financial Domain","date":"2017-04-19","arxiv_id":"1704.05571","n_code_links":0,"syntology":null},{"paper":null,"slug":"effective-search-space-reduction-for-spell","title":"Effective search space reduction for spell correction using character neural embeddings","date":"2017-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/efficient-estimation-of-word-representations","slug":"efficient-estimation-of-word-representations","title":"Efficient Estimation of Word Representations in Vector Space","date":"2013-01-16","arxiv_id":"1301.3781","n_code_links":84,"syntology":{"ran":43,"of":62,"n_ran_checked":38,"n_instrument":5,"unverified":19,"pointer_only":19,"phrase":"43 ran (of which 7 constructed an object rather than computing a result; 38 with no instrument failure: 4 honoured, 0 violated, 34 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified","official":{"repos":["mindspore-courses/DeepNLP-models-MindSpore"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}}],"papers_shown":14,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":14,"with_a_code_link":6,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":14,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/method/skip-gram-word2vec/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/skip-gram-word2vec/papers/ran/1","json":"/method/skip-gram-word2vec/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/word-embeddings","name":"Word Embeddings","papers":3},{"task":"/task/graph-embedding","name":"Graph Embedding","papers":2},{"task":"/task/knowledge-graph-embedding","name":"Knowledge Graph Embedding","papers":2},{"task":"/task/knowledge-graphs","name":"Knowledge Graphs","papers":2},{"task":"/task/anatomy","name":"Anatomy","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/clinical-assertion-status-detection","name":"Clinical Assertion Status Detection","papers":1},{"task":"/task/clinical-concept-extraction","name":"Clinical Concept Extraction","papers":1},{"task":"/task/drug-discovery","name":"Drug Discovery","papers":1},{"task":"/task/feature-engineering","name":"Feature Engineering","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/knowledge-graph-embeddings","name":"Knowledge Graph Embeddings","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/link-prediction","name":"Link Prediction","papers":1},{"task":"/task/multiple-choice","name":"Multiple-choice","papers":1},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":1},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":1},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":1}],"tasks_shown":20,"n_tasks":38,"usage_by_year":[{"year":"2013","papers":1},{"year":"2017","papers":2},{"year":"2019","papers":2},{"year":"2020","papers":6},{"year":"2022","papers":2},{"year":"2023","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/skip-gram-word2vec"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Skip-gram%20Word2Vec","read_at":"2026-10-05T01:02:07+00:00","query":"Skip-gram Word2Vec","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1301.3781","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Skip-gram Word2Vec' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["GRAM","SKIP","GRAM","GRAM","GRAM","X-GRAM","V-Skip","AI-GRAM"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"ab391c7765b5a9e686e56bf634a86ba73e09930bb01976400ffda7c808900e8f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}