Research breakthrough · curated entry
word2vec puts semantic relations into a vector space
Efficient Estimation of Word Representations in Vector Space
- Date
- January 16, 2013
- Category
- Research breakthrough
- Organization / Model
- Evidence
- 1 source · 1 evidence family
Mikolov's team released word2vec, mapping words into dense vectors with a shallow network while preserving semantic relations. Word embeddings became the standard input representation for pretraining in NLP afterwards.
Curator's note: Cross-checked against the arXiv paper.
Curated sources · 1
-
Paper preprints · arXiv2013-01-16
Efficient Estimation of Word Representations in Vector Space
arxiv.org
Cite this page
This page is a curated static snapshot and can be cited directly. Preferred format GB/T 7714—2025 (electronic resource [EB/OL]); the other 5 styles open below, together with the machine-readable files.
GB/T 7714—2025 (electronic resource [EB/OL])
AI 纪年. word2vec 提出词向量，语义关系进入连续空间[EB/OL]. (2013-01-16)[2026-11-03]. https://aihist.net/e/word2vec-2013.html.
APA 7 · American Psychological Association
AI 纪年. (2013, January 16). word2vec 提出词向量，语义关系进入连续空间 [Web page]. https://aihist.net/e/word2vec-2013.html
MLA 9 · Modern Language Association
"word2vec 提出词向量，语义关系进入连续空间." AI 纪年, 16 Jan. 2013, aihist.net/e/word2vec-2013.html. Accessed 3 Nov. 2026.
Chicago 17 · notes-bibliography
AI 纪年. "word2vec 提出词向量，语义关系进入连续空间." Published Jan. 16, 2013. Accessed Nov. 3, 2026. https://aihist.net/e/word2vec-2013.html.
IEEE · citation-reference list
"word2vec 提出词向量，语义关系进入连续空间," AI 纪年, 16 Jan. 2013. [Online]. Available: https://aihist.net/e/word2vec-2013.html. [Accessed: 3 Nov. 2026].
ACM · author-date variant
AI 纪年. January 16, 2013. word2vec 提出词向量，语义关系进入连续空间. Retrieved November 3, 2026 from https://aihist.net/e/word2vec-2013.html.
All six styles come from one template and can be compared word for word. [引用日期], Accessed, urldate and Y2 all carry this page's build date, 2026-11-03 — a static page is an immutable snapshot, so substitute the date you actually consulted it. The address in every style is the archive's canonical page: this English page translates the same snapshot, and the work keeps its name, so one record cites both. For one-click copying use the same entry in the timeline, which takes the day you opened it. Expand the other styles before printing.