Distributed Representations of Sentences and Documents

E260051

machine learning paper scientific paper

"Distributed Representations of Sentences and Documents" is a seminal machine learning paper that introduced the Paragraph Vector (Doc2Vec) method for learning continuous vector representations of variable-length text such as sentences, paragraphs, and documents.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (4)

Label	Occurrences
Distributed Representations of Sentences and Documents canonical	2
Doc2Vec	1
PV-DBOW	1
Paragraph Vector Distributed Memory	1

How this entity was disambiguated

This entity first appeared as the object of triple T2373685 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Distributed Representations of Sentences and Documents
Context triple: [Quoc V. Le, coAuthorOf, Distributed Representations of Sentences and Documents]

A. Large-Scale Distributed Deep Networks
Large-Scale Distributed Deep Networks is a seminal research work that introduced methods for training deep neural networks efficiently across large-scale distributed computing infrastructure, enabling breakthroughs in modern large-scale AI systems.
B. Adam: A Method for Stochastic Optimization
"Adam: A Method for Stochastic Optimization" is a highly influential machine learning paper that introduces the Adam optimizer, a widely used adaptive gradient-based optimization algorithm for training deep neural networks.
C. “A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
D. “Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
E. Semantic Information Processing
Semantic Information Processing is a landmark 1968 edited volume by Marvin Minsky that helped establish foundational approaches to artificial intelligence, knowledge representation, and natural language understanding.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Distributed Representations of Sentences and Documents
Target entity description: "Distributed Representations of Sentences and Documents" is a seminal machine learning paper that introduced the Paragraph Vector (Doc2Vec) method for learning continuous vector representations of variable-length text such as sentences, paragraphs, and documents.

A. Large-Scale Distributed Deep Networks
Large-Scale Distributed Deep Networks is a seminal research work that introduced methods for training deep neural networks efficiently across large-scale distributed computing infrastructure, enabling breakthroughs in modern large-scale AI systems.
B. Adam: A Method for Stochastic Optimization
"Adam: A Method for Stochastic Optimization" is a highly influential machine learning paper that introduces the Adam optimizer, a widely used adaptive gradient-based optimization algorithm for training deep neural networks.
C. “A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
D. “Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
E. Semantic Information Processing
Semantic Information Processing is a landmark 1968 edited volume by Marvin Minsky that helped establish foundational approaches to artificial intelligence, knowledge representation, and natural language understanding.
F. None of above. chosen

Statements (50)

Predicate	Object
instanceOf	machine learning paper ⓘ scientific paper ⓘ
abbreviation	Distributed Representations of Sentences and Documents self-linksurface differs ⓘ surface form: PV-DBOW PV-DM ⓘ
affiliationOfAuthors	Google ⓘ
application	document classification ⓘ information retrieval ⓘ recommendation systems ⓘ sentiment analysis ⓘ
assumes	semantically similar texts have similar vectors ⓘ
author	Quoc V. Le ⓘ Tomas Mikolov ⓘ
citationImpact	highly cited ⓘ
comparesWith	bag-of-n-grams models ⓘ bag-of-words models ⓘ word2vec ⓘ
demonstrates	improved performance on information retrieval tasks ⓘ improved performance on sentiment analysis tasks ⓘ improved performance on text classification tasks ⓘ
extends	word2vec CBOW model ⓘ word2vec skip-gram model ⓘ
field	machine learning ⓘ natural language processing ⓘ
focusesOn	continuous vector representations of documents ⓘ continuous vector representations of paragraphs ⓘ continuous vector representations of sentences ⓘ
handles	variable-length text ⓘ
influenced	document embedding methods ⓘ sentence embedding methods ⓘ unsupervised representation learning for text ⓘ
introduces	Distributed Representations of Sentences and Documents self-linksurface differs ⓘ surface form: Doc2Vec Paragraph Vector ⓘ
learningType	unsupervised learning ⓘ
optimizationObjective	predict words given paragraph vector alone in DBOW variant ⓘ predict words given paragraph vector and context ⓘ
proposesMethod	Paragraph Vector ⓘ surface form: Paragraph Vector Distributed Bag of Words Distributed Representations of Sentences and Documents self-linksurface differs ⓘ surface form: Paragraph Vector Distributed Memory
publishedIn	ICML ⓘ surface form: ICML 2014 ICML ⓘ surface form: International Conference on Machine Learning
representationType	dense vector embeddings ⓘ
represents	each document as a dense vector ⓘ each paragraph as a dense vector ⓘ each sentence as a dense vector ⓘ
shortTitle	Paragraph Vector paper ⓘ
task	learning distributed representations of text ⓘ
title	Distributed Representations of Sentences and Documents self-link ⓘ
uses	negative sampling ⓘ neural network language models ⓘ stochastic gradient descent ⓘ
year	2014 ⓘ

How these facts were elicited

Referenced by (5)

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

Quoc V. Le → coAuthorOf → Distributed Representations of Sentences and Documents ⓘ

Distributed Representations of Sentences and Documents → title → Distributed Representations of Sentences and Documents self-link ⓘ

Distributed Representations of Sentences and Documents → introduces → Distributed Representations of Sentences and Documents self-linksurface differs ⓘ

this entity surface form: Doc2Vec

Distributed Representations of Sentences and Documents → proposesMethod → Distributed Representations of Sentences and Documents self-linksurface differs ⓘ

this entity surface form: Paragraph Vector Distributed Memory

Distributed Representations of Sentences and Documents → abbreviation → Distributed Representations of Sentences and Documents self-linksurface differs ⓘ

this entity surface form: PV-DBOW

All labels observed (4)

How this entity was disambiguated Show

Statements (50)

How these facts were elicited Show

Referenced by (5)

How this entity was disambiguated

How these facts were elicited