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

<p>As global interactions and trade expand, the relevance of Business English has similarly increased, enhancing the scope of its application. Consequently, there is a growing interest in the research of automated translation technologies for Business English texts. This paper provides an overview of the translation requirements for Business English texts, taking into account their distinct characteristics. We propose a novel neural network translation model that integrates an attention mechanism within the sequence-to-sequence (seq2seq) framework. This model incorporates Bayesian optimization to exploit the strengths and features of intelligent algorithms effectively. Furthermore, the model is enhanced by Gaussian regression and an acquisition function, enabling it to simultaneously search for optimal architectural configurations. Experimental analyses demonstrate that the model’s accuracy improves with increased training iterations. In comparative tests across various datasets, the seq2seq translation model augmented with Bayesian optimization and the attention mechanism achieved the highest BLEU scores. Specifically, it exhibited an average improvement of 1.1 points over models using Bayesian optimization without the attention mechanism, indicating a substantial enhancement in translation accuracy. Practical applications show consistent evaluation results across different datasets, with negative evaluations for text translations remaining below 10%. The findings underscore the high quality of the translations produced by our model for Business English texts, affirming its effectiveness and applicability in professional settings.</p>
</abstract>

As global interactions and trade expand, the relevance of Business English has similarly increased, enhancing the scope of its application. Consequently, there is a growing interest in the research of automated translation technologies for Business English texts. This paper provides an overview of the translation requirements for Business English texts, taking into account their distinct characteristics. We propose a novel neural network translation model that integrates an attention mechanism within the sequence-to-sequence (seq2seq) framework. This model incorporates Bayesian optimization to exploit the strengths and features of intelligent algorithms effectively. Furthermore, the model is enhanced by Gaussian regression and an acquisition function, enabling it to simultaneously search for optimal architectural configurations. Experimental analyses demonstrate that the model’s accuracy improves with increased training iterations. In comparative tests across various datasets, the seq2seq translation model augmented with Bayesian optimization and the attention mechanism achieved the highest BLEU scores. Specifically, it exhibited an average improvement of 1.1 points over models using Bayesian optimization without the attention mechanism, indicating a substantial enhancement in translation accuracy. Practical applications show consistent evaluation results across different datasets, with negative evaluations for text translations remaining below 10%. The findings underscore the high quality of the translations produced by our model for Business English texts, affirming its effectiveness and applicability in professional settings.

Research on Automatic Business English Text Translation Technology Based on Intelligent Computing

Applied Mathematics and Nonlinear Sciences

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

As global interactions and trade expand, the relevance of Business English has similarly increased, enhancing the scope of its application. Consequently, there...

Research on Automatic Business English Text Translation Technology Based on Intelligent Computing

Online veröffentlicht: 05. Juli 2024

Seitenbereich: -

Eingereicht: 14. März 2024

Akzeptiert: 09. Juni 2024

DOI: https://doi.org/10.2478/amns-2024-1617

Schlüsselwörter
Seq2seq model, Bayesian optimization, Gaussian regression, Collection function, Business English

© 2024 Honggang Gao, published by Sciendo

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

Research on Automatic Business English Text Translation Technology Based on Intelligent Computing

Online veröffentlicht: 05. Juli 2024

Seitenbereich: -

Eingereicht: 14. März 2024

Akzeptiert: 09. Juni 2024

DOI: https://doi.org/10.2478/amns-2024-1617

SchlüsselwörterSeq2seq model, Bayesian optimization, Gaussian regression, Collection function, Business English

© 2024 Honggang Gao, published by Sciendo

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

Schlüsselwörter
Seq2seq model, Bayesian optimization, Gaussian regression, Collection function, Business English