03201nam a22004935i 4500 978-981-32-9748-7 DE-He213 20210621121135.0 cr nn 008mamaa 190826s2019 si | s |||| 0|eng d 9789813297487 978-981-32-9748-7 10.1007/978-981-32-9748-7 doi QA76.9.N38 UYQL bicssc COM073000 bisacsh UYQL thema 006.35 23 Cheng, Yong. author. aut http://id.loc.gov/vocabulary/relators/aut Joint Training for Neural Machine Translation [electronic resource] / by Yong Cheng. 1st ed. 2019. Singapore : Springer Singapore : Imprint: Springer, 2019. XIII, 78 p. 23 illus., 9 illus. in color. online resource. text txt rdacontent computer c rdamedia online resource cr rdacarrier text file PDF rda Springer Theses, Recognizing Outstanding Ph.D. Research, 2190-5053 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. Natural language processing (Computer science). Artificial intelligence. Computer logic. Natural Language Processing (NLP). https://scigraph.springernature.com/ontologies/product-market-codes/I21040 Logic in AI. https://scigraph.springernature.com/ontologies/product-market-codes/I21020 SpringerLink (Online service) Springer Nature eBook Printed edition: 9789813297470 Printed edition: 9789813297494 Springer Theses, Recognizing Outstanding Ph.D. Research, 2190-5053 https://doi.org/10.1007/978-981-32-9748-7 ZDB-2-SCS ZDB-2-SXCS Computer Science (SpringerNature-11645) Computer Science (R0) (SpringerNature-43710)