The mechanism of additive composition

DOI10.1007/s10994-017-5634-8zbMath1456.68218arXiv1511.08407OpenAlexW3102675873WikidataQ59606529 ScholiaQ59606529MaRDI QIDQ1697927

Naoaki Okazaki, Kentaro Inui, Ran Tian

Publication date: 20 February 2018

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1511.08407

zbMATH Keywords

compositional distributional semanticsapproximation error boundsbias and variancehierarchical Pitman-Yor processnatural language data

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Central limit and other weak theorems (60F05) Random measures (60G57) Natural language processing (68T50)

Uses Software

• word2vec
• AdaGrad
• plfit
• GloVe
• AutoExtend

Cites Work

• Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
• Generalization bounds for function approximation from scattered noisy data
• Similarity-based models of word cooccurrence probabilities
• The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator
• Combinatorial stochastic processes. Ecole d'Eté de Probabilités de Saint-Flour XXXII -- 2002.
• Power-Law Distributions in Empirical Data
• From Frequency to Meaning: Vector Space Models of Semantics
• Beyond the Zipf-Mandelbrot law in quantitative linguistics
• Error bounds for approximation with neural networks
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: The mechanism of additive composition