Papers › Notes on Noise Contrastive Estimation and Negative Sampling

Notes on Noise Contrastive Estimation and Negative Sampling

30 Oct 2014arXiv:1410.8251archive 2025-07-28

Chris Dyer

Estimating the parameters of probabilistic models of language such as maxent models and probabilistic neural models is computationally difficult since it involves evaluating partition functions by summing over an entire vocabulary, which may be millions of word types in size. Two closely related strategies---noise contrastive estimation (Mnih and Teh, 2012; Mnih and Kavukcuoglu, 2013; Vaswani et al., 2013) and negative sampling (Mikolov et al., 2012; Goldberg and Levy, 2014)---have emerged as popular solutions to this computational problem, but some confusion remains as to which is more appropriate and when. This document explicates their relationships to each other and to other estimation techniques. The analysis shows that, although they are superficially similar, NCE is a general parameter estimation technique that is asymptotically unbiased, while negative sampling is best understood as a family of binary classification models that are useful for learning word representations but not as a general-purpose estimator.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

dhyeon/ingredient-vectors mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Distributed Representations of Words and Phrases and their Compositionality (arXiv:1310.4546; that paper's own run record: 21 ran (of which 2 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
hithisisdhara/doc2vec mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Document Embedding with Paragraph Vectors (arXiv:1507.07998; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
inejc/paragraph-vectors mentioned on GitHubpytorchMITSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Binary Classificationparameter estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections