Research on self-training neural machine translation based on monolingual priority sampling
To enhance the performance of neural machine translation (NMT) and ameliorate the detrimental impact of high uncertainty in monolingual data during the self-training process, a self-training NMT model based on priority sampling was proposed. Initially, syntactic dependency trees were constructed and...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2024-04-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024066/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539233380040704 |
|---|---|
| author | ZHANG Xiaoyan PANG Lei DU Xiaofeng LU Tianbo XIA Yamei |
| author_facet | ZHANG Xiaoyan PANG Lei DU Xiaofeng LU Tianbo XIA Yamei |
| author_sort | ZHANG Xiaoyan |
| collection | DOAJ |
| description | To enhance the performance of neural machine translation (NMT) and ameliorate the detrimental impact of high uncertainty in monolingual data during the self-training process, a self-training NMT model based on priority sampling was proposed. Initially, syntactic dependency trees were constructed and the importance of monolingual tokenization was assessed using grammar dependency analysis. Subsequently, a monolingual lexicon was built, and priority was defined based on the importance of monolingual tokenization and uncertainty. Finally, monolingual priorities were computed, and sampling was carried out based on these priorities, consequently generating a synthetic parallel dataset for training the student NMT model. Experimental results on a large-scale subset of the WMT English to German dataset demonstrate that the proposed model effectively enhances NMT translation performance and mitigates the impact of high uncertainty on the model. |
| format | Article |
| id | doaj-art-d0219d6206fb4b7abe0f86d7555e79a8 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2024-04-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-d0219d6206fb4b7abe0f86d7555e79a82025-01-14T07:24:15ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2024-04-0145657259254912Research on self-training neural machine translation based on monolingual priority samplingZHANG XiaoyanPANG LeiDU XiaofengLU TianboXIA YameiTo enhance the performance of neural machine translation (NMT) and ameliorate the detrimental impact of high uncertainty in monolingual data during the self-training process, a self-training NMT model based on priority sampling was proposed. Initially, syntactic dependency trees were constructed and the importance of monolingual tokenization was assessed using grammar dependency analysis. Subsequently, a monolingual lexicon was built, and priority was defined based on the importance of monolingual tokenization and uncertainty. Finally, monolingual priorities were computed, and sampling was carried out based on these priorities, consequently generating a synthetic parallel dataset for training the student NMT model. Experimental results on a large-scale subset of the WMT English to German dataset demonstrate that the proposed model effectively enhances NMT translation performance and mitigates the impact of high uncertainty on the model.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024066/machine translationdata augmentationself-traininguncertaintysyntactic dependency |
| spellingShingle | ZHANG Xiaoyan PANG Lei DU Xiaofeng LU Tianbo XIA Yamei Research on self-training neural machine translation based on monolingual priority sampling Tongxin xuebao machine translation data augmentation self-training uncertainty syntactic dependency |
| title | Research on self-training neural machine translation based on monolingual priority sampling |
| title_full | Research on self-training neural machine translation based on monolingual priority sampling |
| title_fullStr | Research on self-training neural machine translation based on monolingual priority sampling |
| title_full_unstemmed | Research on self-training neural machine translation based on monolingual priority sampling |
| title_short | Research on self-training neural machine translation based on monolingual priority sampling |
| title_sort | research on self training neural machine translation based on monolingual priority sampling |
| topic | machine translation data augmentation self-training uncertainty syntactic dependency |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024066/ |
| work_keys_str_mv | AT zhangxiaoyan researchonselftrainingneuralmachinetranslationbasedonmonolingualprioritysampling AT panglei researchonselftrainingneuralmachinetranslationbasedonmonolingualprioritysampling AT duxiaofeng researchonselftrainingneuralmachinetranslationbasedonmonolingualprioritysampling AT lutianbo researchonselftrainingneuralmachinetranslationbasedonmonolingualprioritysampling AT xiayamei researchonselftrainingneuralmachinetranslationbasedonmonolingualprioritysampling |