CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Exploring Diverse Features for Statistical Machine Translation Model Pruning
Tu, Mei; Zhou, Yu; Zong, Chengqing
2015-11-01
发表期刊IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
卷号23期号:11页码:1847-1857
文章类型Article
摘要In phrase-based and hierarchical phrase-based statistical machine translation systems, translation performance depends heavily on the size and quality of the translation table. To meet the requirements of making a real-time response, some research has been performed to filter the translation table. However, most existing methods are always based on one or two constraints that act as hard rules, such as not allowing phrase-pairs with low translation probabilities. These approaches sometimes make constraints rigid because they consider only a single factor instead of composite factors. Based on the considerations above, in this paper, we propose a machine learning-based framework that integrates multiple features for translation model pruning. Experimental results show that our framework is effective by pruning 80% of the phrase-pairs and 70% of the hierarchical rules, while retaining the quality of the translation models when using the BLEU evaluation metric. Our study further shows that our method can select the most useful phrase-pairs and rules, including those that are low in frequency but still very useful.
关键词Classification Statistical Machine Translation (Smt) Syntactic Constraints Translation Model Pruning
WOS标题词Science & Technology ; Technology
DOI10.1109/TASLP.2015.2456413
收录类别SCI
语种英语
WOS研究方向Acoustics ; Engineering
WOS类目Acoustics ; Engineering, Electrical & Electronic
WOS记录号WOS:000360835000012
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/8979
专题模式识别国家重点实验室_自然语言处理
通讯作者Tu, Mei
作者单位Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Tu, Mei,Zhou, Yu,Zong, Chengqing. Exploring Diverse Features for Statistical Machine Translation Model Pruning[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2015,23(11):1847-1857.
APA Tu, Mei,Zhou, Yu,&Zong, Chengqing.(2015).Exploring Diverse Features for Statistical Machine Translation Model Pruning.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,23(11),1847-1857.
MLA Tu, Mei,et al."Exploring Diverse Features for Statistical Machine Translation Model Pruning".IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 23.11(2015):1847-1857.
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
IEEE-TM.pdf(1725KB)期刊论文作者接受稿开放获取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
[Tu, Mei]的文章
[Zhou, Yu]的文章
[Zong, Chengqing]的文章
百度学术
百度学术中相似的文章
[Tu, Mei]的文章
[Zhou, Yu]的文章
[Zong, Chengqing]的文章
必应学术
必应学术中相似的文章
[Tu, Mei]的文章
[Zhou, Yu]的文章
[Zong, Chengqing]的文章
相关权益政策
暂无数据
收藏/分享
文件名: IEEE-TM.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。