Bilingually-Constrained Recursive Neural Networks with Syntactic Constraints for Hierarchical Translation Model
Chen W(陈炜); Xu B(徐波); Chen,Wei
2015-10
会议名称Natural Language Processing and Chinese Computing (NLPCC)
会议录名称Natural Language Processing and Chinese Computing (NLPCC)
会议日期2015-10
会议地点Nanchang,China
摘要Hierarchical phrase-based translation models have advanced statistical machine translation (SMT). Because such models can improve leveraging of syntactic information, two types of methods (leveraging source parsing and leveraging shallow parsing) are applied to introduce syntactic constraints into translation models. In this paper, we propose a bilingually-constrained recursive neural network (BC-RNN) model to combine the merits of these two types of methods. First we perform supervised learning on a manually parsed corpus using the standard recursive neural network (RNN) model. Then we employ unsupervised bilingually-constrained tuning to improve the accuracy of the standard RNN model. Leveraging the BC-RNN model, we introduce both source parsing and shallow parsing information into a hierarchical phrase-based translation model. The evaluation demonstrates that our proposed method outperforms other state-of-the-art statistical machine translation methods for National Institute of Standards and Technology 2008 (NIST 2008) Chinese-English machine translation testing data.
关键词Machine Translation Neural Network Syntactic
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11803
专题数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者Chen,Wei
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Chen W,Xu B,Chen,Wei. Bilingually-Constrained Recursive Neural Networks with Syntactic Constraints for Hierarchical Translation Model[C],2015.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2.pdf(195KB)会议论文 开放获取CC BY-NC-SA浏览 下载
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
[Chen W(陈炜)]的文章
[Xu B(徐波)]的文章
[Chen,Wei]的文章
百度学术
百度学术中相似的文章
[Chen W(陈炜)]的文章
[Xu B(徐波)]的文章
[Chen,Wei]的文章
必应学术
必应学术中相似的文章
[Chen W(陈炜)]的文章
[Xu B(徐波)]的文章
[Chen,Wei]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2.pdf
格式: Adobe PDF
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。