Neural Machine Translation of Electrical Engineering Based on Integrated Convolutional Neural Networks
Research has shown that neural machine translation performs poorly on low-resource and specific domain parallel corpora. In this paper, we focus on the problem of neural machine translation in the field of electrical engineering. To address the mistranslation caused by the Transformer model’s limite...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/17/3604 |
| _version_ | 1797582683959721984 |
|---|---|
| author | Zikang Liu Yuan Chen Juwei Zhang |
| author_facet | Zikang Liu Yuan Chen Juwei Zhang |
| author_sort | Zikang Liu |
| collection | DOAJ |
| description | Research has shown that neural machine translation performs poorly on low-resource and specific domain parallel corpora. In this paper, we focus on the problem of neural machine translation in the field of electrical engineering. To address the mistranslation caused by the Transformer model’s limited ability to extract feature information from certain sentences, we propose two new models that integrate a convolutional neural network as a feature extraction layer into the Transformer model. The feature information extracted by the CNN is fused separately in the source-side and target-side models, which enhances the Transformer model’s ability to extract feature information, optimizes model performance, and improves translation quality. On the dataset of the field of electrical engineering, the proposed source-side and target-side models improved BLEU scores by 1.63 and 1.12 percentage points, respectively, compared to the baseline model. In addition, the two models proposed in this paper can learn rich semantic knowledge without relying on auxiliary knowledge such as part-of-speech tagging and named entity recognition, which saves a certain amount of human resources and time costs. |
| first_indexed | 2024-03-10T23:24:54Z |
| format | Article |
| id | doaj.art-a3b35d533ab4447b845e79fc0a0f086f |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T23:24:54Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-a3b35d533ab4447b845e79fc0a0f086f2023-11-19T08:01:30ZengMDPI AGElectronics2079-92922023-08-011217360410.3390/electronics12173604Neural Machine Translation of Electrical Engineering Based on Integrated Convolutional Neural NetworksZikang Liu0Yuan Chen1Juwei Zhang2School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, ChinaSchool of Foreign Languages, Henan University of Science and Technology, Luoyang 471023, ChinaSchool of Information Engineering, Henan University of Science and Technology, Luoyang 471023, ChinaResearch has shown that neural machine translation performs poorly on low-resource and specific domain parallel corpora. In this paper, we focus on the problem of neural machine translation in the field of electrical engineering. To address the mistranslation caused by the Transformer model’s limited ability to extract feature information from certain sentences, we propose two new models that integrate a convolutional neural network as a feature extraction layer into the Transformer model. The feature information extracted by the CNN is fused separately in the source-side and target-side models, which enhances the Transformer model’s ability to extract feature information, optimizes model performance, and improves translation quality. On the dataset of the field of electrical engineering, the proposed source-side and target-side models improved BLEU scores by 1.63 and 1.12 percentage points, respectively, compared to the baseline model. In addition, the two models proposed in this paper can learn rich semantic knowledge without relying on auxiliary knowledge such as part-of-speech tagging and named entity recognition, which saves a certain amount of human resources and time costs.https://www.mdpi.com/2079-9292/12/17/3604neural machine translationfeature informationconvolutional neural networkelectrical engineeringlow resource |
| spellingShingle | Zikang Liu Yuan Chen Juwei Zhang Neural Machine Translation of Electrical Engineering Based on Integrated Convolutional Neural Networks Electronics neural machine translation feature information convolutional neural network electrical engineering low resource |
| title | Neural Machine Translation of Electrical Engineering Based on Integrated Convolutional Neural Networks |
| title_full | Neural Machine Translation of Electrical Engineering Based on Integrated Convolutional Neural Networks |
| title_fullStr | Neural Machine Translation of Electrical Engineering Based on Integrated Convolutional Neural Networks |
| title_full_unstemmed | Neural Machine Translation of Electrical Engineering Based on Integrated Convolutional Neural Networks |
| title_short | Neural Machine Translation of Electrical Engineering Based on Integrated Convolutional Neural Networks |
| title_sort | neural machine translation of electrical engineering based on integrated convolutional neural networks |
| topic | neural machine translation feature information convolutional neural network electrical engineering low resource |
| url | https://www.mdpi.com/2079-9292/12/17/3604 |
| work_keys_str_mv | AT zikangliu neuralmachinetranslationofelectricalengineeringbasedonintegratedconvolutionalneuralnetworks AT yuanchen neuralmachinetranslationofelectricalengineeringbasedonintegratedconvolutionalneuralnetworks AT juweizhang neuralmachinetranslationofelectricalengineeringbasedonintegratedconvolutionalneuralnetworks |