A probabilistic matrix factorization algorithm for approximation of sparse matrices in natural language processing

Gianmaria Tarantino

doi:10.1016/j.icte.2018.04.005

2018-06-01

Gianmaria Tarantino *

Stefania Monica

Federico Bergenti

DOI：10.1016/j.icte.2018.04.005

原文链接

查看原文

摘要

En 中文

This paper suggests a variation of a well-known probabilistic matrix factorization algorithm which is commonly used in data analysis and scientific computing, and which has been considered recently to serve natural language processing. The proposed variation is meant to take benefit from the fact that matrices processed in natural language processing tasks are normally sparse rectangular matrices with one dimension much larger than the other, and this can be used to ensure adequate accuracy with acceptable computation time. Preliminary experiments on real-world textual corpora show that the proposed algorithm achieves relevant improvements compared to the original one. (C) 2018 The Korean Institute of Communications and Information Sciences (KICS). Publishing Services by Elsevier B.V.

Keyword:

Latent semantic analysis

Natural language processing

Singular value decomposition