國立虎尾科技大學 |

登入

回首頁

Optimizing Machine Translation by Le...

ProQuest Information and Learning Co.

Optimizing Machine Translation by Learning to Search.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Optimizing Machine Translation by Learning to Search./
作者:	Galron, Daniel.
面頁冊數:	1 online resource (218 pages)
附註:	Source: Dissertation Abstracts International, Volume: 74-04(E), Section: B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781267799647

Optimizing Machine Translation by Learning to Search.
Galron, Daniel.

Optimizing Machine Translation by Learning to Search. - 1 online resource (218 pages)

Source: Dissertation Abstracts International, Volume: 74-04(E), Section: B.

Thesis (Ph.D.)--New York University, 2012.

Includes bibliographical references

We present a novel approach to training discriminative tree-structured machine trans- lation systems by learning to search. We describe three primary innovations in this work: a new parsing coordinator architecture and algorithms to generate the required training examples for the learning algorithm; a new semiring that provides an unbiased way to compare translations; and a new training objective that measures whether a translation inference improves the quality of a translation. We also apply the reinforcement learning concept of exploration to SMT. Finally, we empirically evaluate our innovations.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781267799647Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Optimizing Machine Translation by Learning to Search.
LDR:01709ntm a2200313K 4500 001 915388
005 20180727125214.5
006 m o u
007 cr mn||||a|a||
008 190606s2012 xx obm 000 0 eng d
020 $a 9781267799647
035 $a (MiAaPQ)AAI3546405
035 $a (MiAaPQ)nyu:11300
035 $a AAI3546405
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Galron, Daniel. $3 1188722
245 1 0 $a Optimizing Machine Translation by Learning to Search.
264 0 $c 2012
300 $a 1 online resource (218 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 74-04(E), Section: B.
500 $a Adviser: Dan Melamed.
502 $a Thesis (Ph.D.)--New York University, 2012.
504 $a Includes bibliographical references
520 $a We present a novel approach to training discriminative tree-structured machine trans- lation systems by learning to search. We describe three primary innovations in this work: a new parsing coordinator architecture and algorithms to generate the required training examples for the learning algorithm; a new semiring that provides an unbiased way to compare translations; and a new training objective that measures whether a translation inference improves the quality of a translation. We also apply the reinforcement learning concept of exploration to SMT. Finally, we empirically evaluate our innovations.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a New York University. $b Computer Science. $3 1184382
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3546405 $z click for full text (PQDT)

筆 0 讀者評論

多媒體

評論

新增評論分享你的心得

Export

取書館別