Incorporating bilingual translation templates into neural machine translation
Abstract In the neural machine translation (NMT) paradigm, transformer-based NMT has achieved great progress in recent years. It uses parallel corpus and is based on the stand end-to-end structure. Inspired by the process of translating sentences by translators and the success of templates in other...
| الحاوية / القاعدة: | Scientific Reports |
|---|---|
| المؤلفون الرئيسيون: | , , , , , |
| التنسيق: | مقال |
| اللغة: | الإنجليزية |
| منشور في: |
Nature Portfolio
2025-02-01
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://doi.org/10.1038/s41598-025-86754-w |
| _version_ | 1850010024462516224 |
|---|---|
| author | Fuxue Li Beibei Liu Hong Yan Peijun Xie Jiarui Li Zhen Zhang |
| author_facet | Fuxue Li Beibei Liu Hong Yan Peijun Xie Jiarui Li Zhen Zhang |
| author_sort | Fuxue Li |
| collection | DOAJ |
| container_title | Scientific Reports |
| description | Abstract In the neural machine translation (NMT) paradigm, transformer-based NMT has achieved great progress in recent years. It uses parallel corpus and is based on the stand end-to-end structure. Inspired by the process of translating sentences by translators and the success of templates in other natural language processing tasks, a new method is proposed to incorporate the bilingual translation templates into the Transformer-based NMT. Firstly, the template extraction method is proposed to generate the parallel templates corpus base on the constituency parse tree. Next, given a sentence to be translated, a fuzzy matching method is proposed to calculate the most possible target translation template from the parallel template corpus. Finally, an effective method is proposed to incorporate the bilingual templates into the Transformer-based NMT decoder. Experiment results achieved in three translation tasks show the effectiveness of the proposed approach. |
| format | Article |
| id | doaj-art-ef2b7e9742fb4faea437bfeb07192d17 |
| institution | Directory of Open Access Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| spelling | doaj-art-ef2b7e9742fb4faea437bfeb07192d172025-08-20T00:44:46ZengNature PortfolioScientific Reports2045-23222025-02-0115111310.1038/s41598-025-86754-wIncorporating bilingual translation templates into neural machine translationFuxue Li0Beibei Liu1Hong Yan2Peijun Xie3Jiarui Li4Zhen Zhang5College of Electrical Engineering, Yingkou Institute of TechnologyCollege of Computer Science and Technology, Shenyang University of Chemical TechnologyCollege of Electrical Engineering, Yingkou Institute of TechnologyCollege of Electrical Engineering, Yingkou Institute of TechnologyCollege of Electrical Engineering, Yingkou Institute of TechnologyCollege of Electrical Engineering, Yingkou Institute of TechnologyAbstract In the neural machine translation (NMT) paradigm, transformer-based NMT has achieved great progress in recent years. It uses parallel corpus and is based on the stand end-to-end structure. Inspired by the process of translating sentences by translators and the success of templates in other natural language processing tasks, a new method is proposed to incorporate the bilingual translation templates into the Transformer-based NMT. Firstly, the template extraction method is proposed to generate the parallel templates corpus base on the constituency parse tree. Next, given a sentence to be translated, a fuzzy matching method is proposed to calculate the most possible target translation template from the parallel template corpus. Finally, an effective method is proposed to incorporate the bilingual templates into the Transformer-based NMT decoder. Experiment results achieved in three translation tasks show the effectiveness of the proposed approach.https://doi.org/10.1038/s41598-025-86754-wTranslation templateNeural machine translationConstituency parse treeFuzzy matching strategy |
| spellingShingle | Fuxue Li Beibei Liu Hong Yan Peijun Xie Jiarui Li Zhen Zhang Incorporating bilingual translation templates into neural machine translation Translation template Neural machine translation Constituency parse tree Fuzzy matching strategy |
| title | Incorporating bilingual translation templates into neural machine translation |
| title_full | Incorporating bilingual translation templates into neural machine translation |
| title_fullStr | Incorporating bilingual translation templates into neural machine translation |
| title_full_unstemmed | Incorporating bilingual translation templates into neural machine translation |
| title_short | Incorporating bilingual translation templates into neural machine translation |
| title_sort | incorporating bilingual translation templates into neural machine translation |
| topic | Translation template Neural machine translation Constituency parse tree Fuzzy matching strategy |
| url | https://doi.org/10.1038/s41598-025-86754-w |
| work_keys_str_mv | AT fuxueli incorporatingbilingualtranslationtemplatesintoneuralmachinetranslation AT beibeiliu incorporatingbilingualtranslationtemplatesintoneuralmachinetranslation AT hongyan incorporatingbilingualtranslationtemplatesintoneuralmachinetranslation AT peijunxie incorporatingbilingualtranslationtemplatesintoneuralmachinetranslation AT jiaruili incorporatingbilingualtranslationtemplatesintoneuralmachinetranslation AT zhenzhang incorporatingbilingualtranslationtemplatesintoneuralmachinetranslation |