<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Exploring the evolution of translation of contemporary Chinese literature better presents Chinese literary charm to foreign readers. This paper starts with the Kalman filter algorithm and introduces its cost function that satisfies the error minimization and the Kalman filter gain. Then the BP neural network is illustrated, its minimization of mean square error is solved using the backpropagation algorithm, and the momentum factor is introduced to update the weight function of the BP neural network. The correlation between the Kalman gain and the filtering error is fitted using BP neural network to optimize the Kalman filtering algorithm, and the algorithm flow chart of the BP-KF algorithm is given. Finally, the BP-KF algorithm is used to analyze the data on the evolution of translation strategies and translation dissemination channels of contemporary Chinese literature on the Internet. From the evolution of the translation strategy, the number of translated works of additive French literature decreased by 5.28% year-on-year from 2016 to 2020, and the number of translated works of annotated French literature increased by nearly 11 times year-on-year from 2016 to 2020. In terms of the evolution of the translation and dissemination channels, the percentage of using the Internet to disseminate literary translation and mediation works reviews increased from 16.29% in 2017 to 41.65% in 2021, an increase of 25.36 percentage points. Based on the BP-KF algorithm, the evolution of translation of contemporary Chinese literature can be effectively analyzed, and the data can visually show the direction of the evolution of literary translation, thus expanding the influence of contemporary Chinese literature.</p>
</abstract>

Exploring the evolution of translation of contemporary Chinese literature better presents Chinese literary charm to foreign readers. This paper starts with the Kalman filter algorithm and introduces its cost function that satisfies the error minimization and the Kalman filter gain. Then the BP neural network is illustrated, its minimization of mean square error is solved using the backpropagation algorithm, and the momentum factor is introduced to update the weight function of the BP neural network. The correlation between the Kalman gain and the filtering error is fitted using BP neural network to optimize the Kalman filtering algorithm, and the algorithm flow chart of the BP-KF algorithm is given. Finally, the BP-KF algorithm is used to analyze the data on the evolution of translation strategies and translation dissemination channels of contemporary Chinese literature on the Internet. From the evolution of the translation strategy, the number of translated works of additive French literature decreased by 5.28% year-on-year from 2016 to 2020, and the number of translated works of annotated French literature increased by nearly 11 times year-on-year from 2016 to 2020. In terms of the evolution of the translation and dissemination channels, the percentage of using the Internet to disseminate literary translation and mediation works reviews increased from 16.29% in 2017 to 41.65% in 2021, an increase of 25.36 percentage points. Based on the BP-KF algorithm, the evolution of translation of contemporary Chinese literature can be effectively analyzed, and the data can visually show the direction of the evolution of literary translation, thus expanding the influence of contemporary Chinese literature.

An analysis of the translation process of contemporary Chinese literature based on the Kalman filter algorithm

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Exploring the evolution of translation of contemporary Chinese literature better presents Chinese literary charm to foreign readers. This paper starts with the...

An analysis of the translation process of contemporary Chinese literature based on the Kalman filter algorithm

Publié en ligne: 26 juil. 2023

Pages: -

Reçu: 14 août 2022

Accepté: 03 févr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00095

Mots clés
Kalman filtering algorithm, BP neural network, Backpropagation algorithm, Literary translation

© 2023 Qing Xie, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

An analysis of the translation process of contemporary Chinese literature based on the Kalman filter algorithm

Publié en ligne: 26 juil. 2023

Pages: -

Reçu: 14 août 2022

Accepté: 03 févr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00095

Mots clésKalman filtering algorithm, BP neural network, Backpropagation algorithm, Literary translation

© 2023 Qing Xie, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Kalman filtering algorithm, BP neural network, Backpropagation algorithm, Literary translation