Joint Training for Neural Machine Translation

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 matric...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριος συγγραφέας: Cheng, Yong (Συγγραφέας, http://id.loc.gov/vocabulary/relators/aut)
Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
Γλώσσα:English
Έκδοση: Singapore : Springer Singapore : Imprint: Springer, 2019.
Έκδοση:1st ed. 2019.
Σειρά:Springer Theses, Recognizing Outstanding Ph.D. Research,
Θέματα:
Διαθέσιμο Online:Full Text via HEAL-Link
LEADER 03139nam a2200481 4500
001 978-981-32-9748-7
003 DE-He213
005 20190826080853.0
007 cr nn 008mamaa
008 190826s2019 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 
040 |d GrThAP 
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 
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). 
650 0 |a Artificial intelligence. 
650 0 |a Computer logic. 
650 1 4 |a Natural Language Processing (NLP).  |0 http://scigraph.springernature.com/things/product-market-codes/I21040 
650 2 4 |a Logic in AI.  |0 http://scigraph.springernature.com/things/product-market-codes/I21020 
710 2 |a SpringerLink (Online service) 
773 0 |t Springer eBooks 
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 
856 4 0 |u https://doi.org/10.1007/978-981-32-9748-7  |z Full Text via HEAL-Link 
912 |a ZDB-2-SCS 
950 |a Computer Science (Springer-11645)