Efficient Estimation of Word Representations in Vector Space

E906311

conference paper scientific paper

Efficient Estimation of Word Representations in Vector Space is the influential 2013 paper that introduced the word2vec models for learning distributed word embeddings, significantly advancing natural language processing.

Jump to: Surface forms Statements Referenced by

Observed surface forms (1)

Surface form	Occurrences
Distributed Representations of Words and Phrases and their Compositionality	1

Statements (47)

Predicate	Object
instanceOf	conference paper ⓘ scientific paper ⓘ
affiliationOfAuthors	Google NERFINISHED ⓘ
approach	shallow neural networks ⓘ
author	Greg Corrado NERFINISHED ⓘ Jeffrey Dean NERFINISHED ⓘ Kai Chen NERFINISHED ⓘ Tomas Mikolov NERFINISHED ⓘ
citationStatus	highly cited ⓘ
datasetUsed	Google News corpus NERFINISHED ⓘ
demonstratedProperty	semantic regularities in word embeddings ⓘ syntactic regularities in word embeddings ⓘ word analogies in vector space ⓘ
designedFor	large-scale text corpora ⓘ
embeddingType	word embeddings ⓘ
evaluationTask	word analogy ⓘ word similarity ⓘ
field	computational linguistics ⓘ machine learning ⓘ natural language processing ⓘ
impact	influenced development of modern word embedding methods ⓘ widely adopted in NLP research and applications ⓘ
influenced	GloVe NERFINISHED ⓘ deep learning for NLP ⓘ fastText NERFINISHED ⓘ neural machine translation ⓘ
introducedTerm	word2vec NERFINISHED ⓘ
language	English ⓘ
mainContribution	efficient training of distributed word representations ⓘ introduction of word2vec models ⓘ popularization of neural word embeddings ⓘ
optimizationGoal	efficient estimation of word vectors from large datasets ⓘ
proposedModel	Continuous Bag-of-Words model ⓘ Skip-gram model NERFINISHED ⓘ
publicationYear	2013 ⓘ
relatedConcept	distributed representations ⓘ neural language models ⓘ vector space semantics ⓘ
shortTitle	word2vec paper ⓘ
task	language modeling ⓘ learning distributed word representations ⓘ
technique	hierarchical softmax ⓘ negative sampling ⓘ
title	Efficient Estimation of Word Representations in Vector Space NERFINISHED ⓘ
trainingObjective	predicting context words from target word ⓘ predicting target word from context words ⓘ
trainingSpeed	significantly faster than previous neural language models ⓘ

Referenced by (2)

Full triples — surface form annotated when it differs from this entity's canonical label.

Tomas Mikolov → notableWork → Efficient Estimation of Word Representations in Vector Space ⓘ

this entity surface form: Distributed Representations of Words and Phrases and their Compositionality