Multi-Task Neural Model for Agglutinative Language Translation | |
Pan, YR (Pan, Yirong) 1 , 2 , 3; Li, X (Li, Xiao) 1 , 2 , 3; Yang, YT (Yang, Yating) 1 , 2 , 3; Dong, R (Dong, Rui) 1 , 2 , 3 | |
2020 | |
会议日期 | JUL 05-10, 2020 |
会议地点 | ELECTR NETWORK |
英文摘要 | Neural machine translation (NMT) has achieved impressive performance recently by using large-scale parallel corpora. However, it struggles in the low-resource and morphologically-rich scenarios of agglutinative language translation task. Inspired by the finding that monolingual data can greatly improve the NMT performance, we propose a multi-task neural model that jointly learns to perform bi-directional translation and agglutinative language stemming Our approach employs the shared encoder and decoder to train a single model without changing the standard NMT architecture but instead adding a token before each source-side sentence to specify the desired target outputs of the two different tasks. Experimental results on Turkish-English and Uyghur-Chinese show that our proposed approach can significantly improve the translation performance on agglutinative languages by using a small amount of monolingual data. |
会议录 | ASSOC COMPUTATIONAL LINGUISTICS-ACL209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA
![]() |
ISSN号 | 978-1-952148-03-3 |
内容类型 | 会议论文 |
源URL | [http://ir.xjipc.cas.cn/handle/365002/7880] ![]() |
专题 | 新疆理化技术研究所_多语种信息技术研究室 |
作者单位 | 1.Xinjiang Lab Minor Speech & Language Informat Pro, Urumqi, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Chinese Acad Sci, Xinjiang Tech Inst Phys & Chem, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Pan, YR ,Li, X ,Yang, YT ,et al. Multi-Task Neural Model for Agglutinative Language Translation[C]. 见:. ELECTR NETWORK. JUL 05-10, 2020. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论