Who Cited It

Don't count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors

2014 · 1,388 citations · 5 from inside this corpus

Marco Baroni, Georgiana Dinu low, Germán Kruszewski low

Context-predicting models (more commonly known as embeddings or neural language models) are the new kids on the distributional semantics block. Despite the buzz surrounding these models, the literature is still lacking a systematic comparison of the predictive models with classic, count-vector-based distributional semantic approaches. In this paper, we perform such an extensive evaluation, on a wide range of lexical semantics tasks and across many parameter settings. The results, to our own surprise, show that the buzz is fully justified, as the context-predicting models obtain a thorough and resounding victory against their count-based counterparts.

Don't count, predict! A systematic comparison of context-counting vs. context-predicting … (2014)Don't count, predict! A syste…Latent dirichlet allocation (2003)Latent dirichlet allocationEfficient Estimation of Word Representations in Vector Space (2013)Efficient Estimation of Word …Distributed Representations of Words and Phrases and their Compositionality (2013)Distributed Representations o…Efficient Estimation of Word Representations in Vector Space (2013)Efficient Estimation of Word …A solution to Plato's problem: The latent semantic analysis theory of acquisition, induct… (1997)A solution to Plato's problem…A unified architecture for natural language processing (2008)A unified architecture for na…Natural Language Processing (almost) from Scratch (2011)Natural Language Processing (…Natural Language Processing (almost) from Scratch (2011)Natural Language Processing (…From Frequency to Meaning: Vector Space Models of Semantics (2010)From Frequency to Meaning: Ve…Linguistic Regularities in Continuous Space Word Representations (2013)Linguistic Regularities in Co…A neural probabilistic language model (2003)A neural probabilistic langua…DeViSE: A Deep Visual-Semantic Embedding Model (2013)DeViSE: A Deep Visual-Semanti…Word Representations: A Simple and General Method for Semi-Supervised Learning (2010)Word Representations: A Simpl…Contextual correlates of synonymy (1965)Contextual correlates of syno…Exploiting Similarities among Languages for Machine Translation (2013)Exploiting Similarities among…Glove: Global Vectors for Word Representation (2014)Glove: Global Vectors for Wor…Recurrent Convolutional Neural Networks for Text Classification (2015)Recurrent Convolutional Neura…Language Models as Knowledge Bases? (2019)Language Models as Knowledge …Neural Word Embedding as Implicit Matrix Factorization (2014)Neural Word Embedding as Impl…Document Modeling with Gated Recurrent Neural Network for Sentiment Classification (2015)Document Modeling with Gated …
20 of 20 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.
this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

What this paper cites, inside the corpus

PaperYearCited
Latent dirichlet allocation200327,078
Efficient Estimation of Word Representations in Vector Space201318,186
Distributed Representations of Words and Phrases and their Compositionality201318,054
Efficient Estimation of Word Representations in Vector Space201311,714
A solution to Plato's problem: The latent semantic analysis theory of acquisition, induct…19976,147
A unified architecture for natural language processing20085,207
Natural Language Processing (almost) from Scratch20115,174
Natural Language Processing (almost) from Scratch20113,991
From Frequency to Meaning: Vector Space Models of Semantics20102,902
Linguistic Regularities in Continuous Space Word Representations20132,885
A neural probabilistic language model20032,675
DeViSE: A Deep Visual-Semantic Embedding Model20132,068
Word Representations: A Simple and General Method for Semi-Supervised Learning20101,941
Contextual correlates of synonymy19651,450
Exploiting Similarities among Languages for Machine Translation20131,442

What cites it, inside the corpus

PaperYearCited
Glove: Global Vectors for Word Representation201434,067
Recurrent Convolutional Neural Networks for Text Classification20152,314
Language Models as Knowledge Bases?20191,798
Neural Word Embedding as Implicit Matrix Factorization20141,591
Document Modeling with Gated Recurrent Neural Network for Sentiment Classification20151,548

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Topic ModelingComputer Science
Natural Language Processing TechniquesComputer Science
Multimodal Machine Learning ApplicationsComputer Science

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

  • supports3 author record(s) attached.
  • supports53 reference(s) recorded.
  • neutralThe DOI carries no year to check against.
  • supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:59+00:00.

sha256 59007f057c7dae86…