Modelling of word usage frequency dynamics using artificial neural network

2nd International Conference on Mathematical Modeling in Physical Sciences 2013

物理学;数学

Maslennikova, Yu.S.^1 ; Bochkarev, V.V.^1 ; Voloskov, D.S.^1

Kazan Federal University, Kremlevskaya str.18, Kazan 420018, Russia^1

关键词: Analysis and verifications;    Filtering algorithm;    Frequency dynamics;    Large amounts;    Maximum likelihood criteria;    Optimal fitting;    Statistical modelling;    Trend model;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/490/1/012180/pdf
DOI  :  10.1088/1742-6596/490/1/012180

来源: IOP

【 摘 要 】

In this paper the method for modelling of word usage frequency time series is proposed. An artificial feedforward neural network was used to predict word usage frequencies. The neural network was trained using the maximum likelihood criterion. The Google Books Ngram corpus was used for the analysis. This database provides a large amount of data on frequency of specific word forms for 7 languages. Statistical modelling of word usage frequency time series allows finding optimal fitting and filtering algorithm for subsequent lexicographic analysis and verification of frequency trend models.