: NLP Vocabulary: principal component analysis

NLP methods and tools > statistics > dimensionality reduction > feature selection > principal component analysis

principal component analysis

Principal components analysis (PCA) is a method of dimensionality reduction. (Popescu & Dinu, 2009)

A principal components analysis can also be performed on the selected features to see if they reflect any plausible semantic space. (Murphy, Baroni & Poesio, 2009)
Before explaining ICA we briefly explain PCA widely used for dimensionality reduction and whitening or sphering of feature vectors. (Yamagiwa, Oyama & Shimodaira, 2023)
To tackle this problem we utilize PCA (Principal Component Analysis) to get variances along each axes which are represented by eigenvalues of covariance matrix subtracted the mean of each latent vectors. (Zou, Li, Liu & Deng, 2018)
We apply PCA (Principal Component Analysis) to reduce the dimensionality of sentence embeddings to represent them in a two-dimensional space. (Niu, Xiong, Wang, Yu, Zhang & Yang, 2023)
We experimented with principal component analysis (PCA) and t-SNE (Van der Maaten and Hinton 2008) and found that at DMscale dimensionality these took too long and were too computationally intensive to resolve a query in web-appropriate time. (Sayeed, Hong & Demberg, 2016)

http://data.loterre.fr/ark:/67375/8LP-TRRMDS7R-R

RDF/XML TURTLE JSON-LD Last modified 7/1/24

Loterre