國立虎尾科技大學 |

Joint Training for Neural Machine Translation

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Joint Training for Neural Machine Translation/ by Yong Cheng.
作者:	Cheng, Yong.
面頁冊數:	XIII, 78 p. 23 illus., 9 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Natural language processing (Computer science). -
電子資源:	https://doi.org/10.1007/978-981-32-9748-7
ISBN:	9789813297487

Joint Training for Neural Machine Translation
Cheng, Yong.

Joint Training for Neural Machine Translation[electronic resource] /by Yong Cheng. - 1st ed. 2019. - XIII, 78 p. 23 illus., 9 illus. in color.online resource. - Springer Theses, Recognizing Outstanding Ph.D. Research,2190-5053. - Springer Theses, Recognizing Outstanding Ph.D. Research,.

1. Introduction -- 2. Neural Machine Translation -- 3. Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation -- 4. Semi-supervised Learning for Neural Machine Translation -- 5. Joint Training for Pivot-based Neural Machine Translation -- 6. Joint Modeling for Bidirectional Neural Machine Translation with Contrastive Learning -- 7. Related Work -- 8. Conclusion.

This book presents four approaches to jointly training bidirectional neural machine translation (NMT) models. First, in order to improve the accuracy of the attention mechanism, it proposes an agreement-based joint training approach to help the two complementary models agree on word alignment matrices for the same training data. Second, it presents a semi-supervised approach that uses an autoencoder to reconstruct monolingual corpora, so as to incorporate these corpora into neural machine translation. It then introduces a joint training algorithm for pivot-based neural machine translation, which can be used to mitigate the data scarcity problem. Lastly it describes an end-to-end bidirectional NMT model to connect the source-to-target and target-to-source translation models, allowing the interaction of parameters between these two directional models.

ISBN: 9789813297487

Standard No.: 10.1007/978-981-32-9748-7doiSubjects--Topical Terms:

802180
Natural language processing (Computer science).

LC Class. No.: QA76.9.N38

Dewey Class. No.: 006.35

Joint Training for Neural Machine Translation
LDR:02620nam a22003975i 4500 001 1009917
003 DE-He213
005 20200704201045.0
007 cr nn 008mamaa
008 210106s2019 si | s |||| 0|eng d
020 $a 9789813297487 $9 978-981-32-9748-7
024 7 $a 10.1007/978-981-32-9748-7 $2 doi
035 $a 978-981-32-9748-7
050 4 $a QA76.9.N38
072 7 $a UYQL $2 bicssc
072 7 $a COM073000 $2 bisacsh
072 7 $a UYQL $2 thema
082 0 4 $a 006.35 $2 23
100 1 $a Cheng, Yong. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1303938
245 1 0 $a Joint Training for Neural Machine Translation $h [electronic resource] / $c by Yong Cheng.
250 $a 1st ed. 2019.
264 1 $a Singapore : $b Springer Singapore : $b Imprint: Springer, $c 2019.
300 $a XIII, 78 p. 23 illus., 9 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a Springer Theses, Recognizing Outstanding Ph.D. Research, $x 2190-5053
505 0 $a 1. Introduction -- 2. Neural Machine Translation -- 3. Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation -- 4. Semi-supervised Learning for Neural Machine Translation -- 5. Joint Training for Pivot-based Neural Machine Translation -- 6. Joint Modeling for Bidirectional Neural Machine Translation with Contrastive Learning -- 7. Related Work -- 8. Conclusion.
520 $a This book presents four approaches to jointly training bidirectional neural machine translation (NMT) models. First, in order to improve the accuracy of the attention mechanism, it proposes an agreement-based joint training approach to help the two complementary models agree on word alignment matrices for the same training data. Second, it presents a semi-supervised approach that uses an autoencoder to reconstruct monolingual corpora, so as to incorporate these corpora into neural machine translation. It then introduces a joint training algorithm for pivot-based neural machine translation, which can be used to mitigate the data scarcity problem. Lastly it describes an end-to-end bidirectional NMT model to connect the source-to-target and target-to-source translation models, allowing the interaction of parameters between these two directional models.
650 0 $a Natural language processing (Computer science). $3 802180
650 0 $a Artificial intelligence. $3 559380
650 0 $a Computer logic. $3 786340
650 1 4 $a Natural Language Processing (NLP). $3 1254293
650 2 4 $a Logic in AI. $3 1228083
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9789813297470
776 0 8 $i Printed edition: $z 9789813297494
830 0 $a Springer Theses, Recognizing Outstanding Ph.D. Research, $x 2190-5053 $3 1253569
856 4 0 $u https://doi.org/10.1007/978-981-32-9748-7
912 $a ZDB-2-SCS
912 $a ZDB-2-SXCS
950 $a Computer Science (SpringerNature-11645)
950 $a Computer Science (R0) (SpringerNature-43710)