大葉大學圖書館 |

登入

回首頁 到查詢結果 [ subject:"Computer Science." ]

On Word Alignment Models for Statist...

University of Rochester.

On Word Alignment Models for Statistical Machine Translation.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
書名/作者:	On Word Alignment Models for Statistical Machine Translation.
作者:	Zhao, Shaojun.
面頁冊數:	120 p.
附註:	Source: Dissertation Abstracts International, Volume: 72-04, Section: B, page: 2221.
Contained By:	Dissertation Abstracts International72-04B.
標題:	Computer Science.
ISBN:	9781124481944
摘要、提要註:	Machine translation remains the holy grail of computational linguistics. All statistical machine translation systems are built upon the idea of word alignment. While the field of word alignment has had tremendous progress in the last two decades, it is still in great need of speed and quality improvement.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3442784

On Word Alignment Models for Statistical Machine Translation.
Zhao, Shaojun.

On Word Alignment Models for Statistical Machine Translation. - 120 p.

Source: Dissertation Abstracts International, Volume: 72-04, Section: B, page: 2221.

Thesis (Ph.D.)--University of Rochester, 2011.

Machine translation remains the holy grail of computational linguistics. All statistical machine translation systems are built upon the idea of word alignment. While the field of word alignment has had tremendous progress in the last two decades, it is still in great need of speed and quality improvement.

ISBN: 9781124481944Subjects--Topical Terms:

423143
Computer Science.

On Word Alignment Models for Statistical Machine Translation.
LDR:01807nam 2200289 4500 001 365277
005 20120516132902.5
008 121018s2011 ||||||||||||||||| ||eng d
020 $a 9781124481944
035 $a (UMI)AAI3442784
035 $a AAI3442784
040 $a UMI $c UMI
100 1 $a Zhao, Shaojun. $3 475300
245 1 0 $a On Word Alignment Models for Statistical Machine Translation.
300 $a 120 p.
500 $a Source: Dissertation Abstracts International, Volume: 72-04, Section: B, page: 2221.
500 $a Adviser: Daniel Gildea.
502 $a Thesis (Ph.D.)--University of Rochester, 2011.
520 $a Machine translation remains the holy grail of computational linguistics. All statistical machine translation systems are built upon the idea of word alignment. While the field of word alignment has had tremendous progress in the last two decades, it is still in great need of speed and quality improvement.
520 $a We designed a fertility hidden Markov model for word alignment, which is dramatically faster than the most widely used 113M Model 4. In fact, our model is even faster and has lower alignment error rate (AER) than the hidden Markov model. An experiment on Chinese-English translation shows that our word alignment model leads to better translation results than IBM Model 4, based on the BLEU metric.
520 $a We also designed algorithms that mine massive and high quality bilingual texts for a variety of language pairs from the web using word alignment. The resulting data improved a state-of-the-art machine translation system.
590 $a School code: 0188.
650 4 $a Computer Science. $3 423143
690 $a 0984
710 2 $a University of Rochester. $3 475298
773 0 $t Dissertation Abstracts International $g 72-04B.
790 1 0 $a Gildea, Daniel, $e advisor
790 $a 0188
791 $a Ph.D.
792 $a 2011
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3442784

筆 0 讀者評論

多媒體

多媒體檔案
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3442784

評論

新增評論分享你的心得

Export

取書館別