Hybrid System Combination Framework for Uyghur–Chinese Machine Translation
Both the statistical machine translation (SMT) model and neural machine translation (NMT) model are the representative models in Uyghur–Chinese machine translation tasks with their own merits. Thus, it will be a promising direction to combine the advantages of them to further improve the translation...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/12/3/98 |
| _version_ | 1797395264702513152 |
|---|---|
| author | Yajuan Wang Xiao Li Yating Yang Azmat Anwar Rui Dong |
| author_facet | Yajuan Wang Xiao Li Yating Yang Azmat Anwar Rui Dong |
| author_sort | Yajuan Wang |
| collection | DOAJ |
| description | Both the statistical machine translation (SMT) model and neural machine translation (NMT) model are the representative models in Uyghur–Chinese machine translation tasks with their own merits. Thus, it will be a promising direction to combine the advantages of them to further improve the translation performance. In this paper, we present a hybrid framework of developing a system combination for a Uyghur–Chinese machine translation task that works in three layers to achieve better translation results. In the first layer, we construct various machine translation systems including SMT and NMT. In the second layer, the outputs of multiple systems are combined to leverage the advantage of SMT and NMT models by using a multi-source-based system combination approach and the voting-based system combination approaches. Moreover, instead of selecting an individual system’s combined outputs as the final results, we transmit the outputs of the first layer and the second layer into the final layer to make a better prediction. Experiment results on the Uyghur–Chinese translation task show that the proposed framework can significantly outperform the baseline systems in terms of both the accuracy and fluency, which achieves a better performance by 1.75 BLEU points compared with the best individual system and by 0.66 BLEU points compared with the conventional system combination methods, respectively. |
| first_indexed | 2024-03-09T00:32:54Z |
| format | Article |
| id | doaj.art-da10c6f3d72944b5b21435fe4a4a857c |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-09T00:32:54Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-da10c6f3d72944b5b21435fe4a4a857c2023-12-11T18:26:30ZengMDPI AGInformation2078-24892021-02-011239810.3390/info12030098Hybrid System Combination Framework for Uyghur–Chinese Machine TranslationYajuan Wang0Xiao Li1Yating Yang2Azmat Anwar3Rui Dong4The Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi 830011, ChinaThe Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi 830011, ChinaThe Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi 830011, ChinaThe Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi 830011, ChinaThe Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi 830011, ChinaBoth the statistical machine translation (SMT) model and neural machine translation (NMT) model are the representative models in Uyghur–Chinese machine translation tasks with their own merits. Thus, it will be a promising direction to combine the advantages of them to further improve the translation performance. In this paper, we present a hybrid framework of developing a system combination for a Uyghur–Chinese machine translation task that works in three layers to achieve better translation results. In the first layer, we construct various machine translation systems including SMT and NMT. In the second layer, the outputs of multiple systems are combined to leverage the advantage of SMT and NMT models by using a multi-source-based system combination approach and the voting-based system combination approaches. Moreover, instead of selecting an individual system’s combined outputs as the final results, we transmit the outputs of the first layer and the second layer into the final layer to make a better prediction. Experiment results on the Uyghur–Chinese translation task show that the proposed framework can significantly outperform the baseline systems in terms of both the accuracy and fluency, which achieves a better performance by 1.75 BLEU points compared with the best individual system and by 0.66 BLEU points compared with the conventional system combination methods, respectively.https://www.mdpi.com/2078-2489/12/3/98statistical machine translation (SMT)neural machine translation (NMT)multi-source-based combinationvoting-based combinationhybrid system combination |
| spellingShingle | Yajuan Wang Xiao Li Yating Yang Azmat Anwar Rui Dong Hybrid System Combination Framework for Uyghur–Chinese Machine Translation Information statistical machine translation (SMT) neural machine translation (NMT) multi-source-based combination voting-based combination hybrid system combination |
| title | Hybrid System Combination Framework for Uyghur–Chinese Machine Translation |
| title_full | Hybrid System Combination Framework for Uyghur–Chinese Machine Translation |
| title_fullStr | Hybrid System Combination Framework for Uyghur–Chinese Machine Translation |
| title_full_unstemmed | Hybrid System Combination Framework for Uyghur–Chinese Machine Translation |
| title_short | Hybrid System Combination Framework for Uyghur–Chinese Machine Translation |
| title_sort | hybrid system combination framework for uyghur chinese machine translation |
| topic | statistical machine translation (SMT) neural machine translation (NMT) multi-source-based combination voting-based combination hybrid system combination |
| url | https://www.mdpi.com/2078-2489/12/3/98 |
| work_keys_str_mv | AT yajuanwang hybridsystemcombinationframeworkforuyghurchinesemachinetranslation AT xiaoli hybridsystemcombinationframeworkforuyghurchinesemachinetranslation AT yatingyang hybridsystemcombinationframeworkforuyghurchinesemachinetranslation AT azmatanwar hybridsystemcombinationframeworkforuyghurchinesemachinetranslation AT ruidong hybridsystemcombinationframeworkforuyghurchinesemachinetranslation |