CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Three Strategies to Improve One-to-Many Multilingual Translation
Wang, Yining1; Zhang, Jiajun1; Zhai, Feifei2; Xu, Jingfang2; Zong, Chengqing1
2018
会议名称EMNLP
会议日期2018-11
会议地点Brussels, Belgium
摘要

Due to the benefits of model compactness, multilingual translation (including many-toone, many-to-many and one-to-many) based on a universal encoder-decoder architecture attracts more and more attention. However, previous studies show that one-to-many translation based on this framework cannot perform on par with the individually trained models. In this work, we introduce three strategies to improve one-to-many multilingual translation by balancing the shared and unique features. Within the architecture of one decoder for all target languages, we first exploit the use of unique initial states for different target languages. Then, we employ language-dependent positional embeddings. Finally and especially, we propose to divide the hidden cells of the decoder into shared and language-dependent ones. The extensive experiments demonstrate that our proposed methods can obtain remarkable improvements over the strong baselines. Moreover, our strategies can achieve comparable or even better performance than the individually trained translation models.

文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/23197
专题模式识别国家重点实验室_自然语言处理
作者单位1.中国科学院自动化研究所
2.搜狗
第一作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Wang, Yining,Zhang, Jiajun,Zhai, Feifei,et al. Three Strategies to Improve One-to-Many Multilingual Translation[C],2018.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Yining]的文章
[Zhang, Jiajun]的文章
[Zhai, Feifei]的文章
百度学术
百度学术中相似的文章
[Wang, Yining]的文章
[Zhang, Jiajun]的文章
[Zhai, Feifei]的文章
必应学术
必应学术中相似的文章
[Wang, Yining]的文章
[Zhang, Jiajun]的文章
[Zhai, Feifei]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。