中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Curriculum pre-training for stylized neural machine translation

文献类型:期刊论文

作者Zou, Aixiao1; Wu, Xuanxuan2; Li, Xinjie3; Zhang, Ting3; Cui, Fuwei4; Xu, Jinan2
刊名APPLIED INTELLIGENCE
出版日期2024-06-18
页码11
关键词Stylized neural machine translation Pre-training model Data augmentation Curriculum learning
ISSN号0924-669X
DOI10.1007/s10489-024-05586-9
通讯作者Xu, Jinan(jaxu@bjtu.edu.cn)
英文摘要Stylized neural machine translation (NMT) aims to translate sentences of one style into sentences of another style, it is essential for the application of machine translation in a real-world scenario. Most existing methods employ an encoder-decoder structure to understand, translate, and transform style simultaneously, which increases the learning difficulty of the model and leads to poor generalization ability. To address these issues, we propose a curriculum pre-training framework to improve stylized NMT. Specifically, we design four pre-training tasks of increasing difficulty to assist the model to extract more features essential for stylized translation. Then, we further propose a stylized-token aligned data augmentation method to expand the scale of pre-training corpus for alleviating the data-scarcity problem. Experiments show that our method achieves competitive results on MTFC and Modern-Classical translation dataset.
资助项目National Natural Science Foundation of China
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001249598200001
出版者SPRINGER
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/59103]  
专题紫东太初大模型研究中心
通讯作者Xu, Jinan
作者单位1.Beijing Wuzi Univ, Sch Informat, Beijing 101149, Peoples R China
2.Beijing Jiaotong Univ, Sch Comp Informat Technol, 3 Shangyuan Rd, Haidian Beijing 100044, Peoples R China
3.Global Tone Commun Technol Co Ltd, 20 Shijingshan Rd, Beijing 100131, Peoples R China
4.Chinese Acad Sci, Inst Automat, 95 East Zhongguancun Rd, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Zou, Aixiao,Wu, Xuanxuan,Li, Xinjie,et al. Curriculum pre-training for stylized neural machine translation[J]. APPLIED INTELLIGENCE,2024:11.
APA Zou, Aixiao,Wu, Xuanxuan,Li, Xinjie,Zhang, Ting,Cui, Fuwei,&Xu, Jinan.(2024).Curriculum pre-training for stylized neural machine translation.APPLIED INTELLIGENCE,11.
MLA Zou, Aixiao,et al."Curriculum pre-training for stylized neural machine translation".APPLIED INTELLIGENCE (2024):11.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。