01112nas 2200385- 450 991089425720332120210111030516.4(OCoLC)863202530(CKB)2670000000481105(CONSER)--2014239007(DE-599)ZDB2738342-8(EXLCZ)99267000000048110520131119b20122014 --- -engur|||||||||||txtrdacontentcrdamediacrrdacarrierISRN geriatricsNew York, NY :Hindawi Publishing Corporation1 online resourceRefereed/Peer-reviewed2314-4750 International Scholarly Research Network geriatricsGeriatricsGeriatricsPeriodicalsGeriatricsfast(OCoLC)fst00941257Periodicals.fastGeriatricsGeriatrics.International Scholarly Research Network,JOURNAL9910894257203321ISRN geriatrics4272609UNINA03100nam 22005055 450 991034930300332120200704201045.0981-329-748-410.1007/978-981-32-9748-7(CKB)4100000009076254(MiAaPQ)EBC5883402(DE-He213)978-981-32-9748-7(PPN)258304693(EXLCZ)99410000000907625420190826d2019 u| 0engurcnu||||||||txtrdacontentcrdamediacrrdacarrierJoint Training for Neural Machine Translation /by Yong Cheng1st ed. 2019.Singapore :Springer Singapore :Imprint: Springer,2019.1 online resource (90 pages)Springer Theses, Recognizing Outstanding Ph.D. Research,2190-5053981-329-747-6 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.Springer Theses, Recognizing Outstanding Ph.D. Research,2190-5053Natural language processing (Computer science)Artificial intelligenceComputer logicNatural Language Processing (NLP)https://scigraph.springernature.com/ontologies/product-market-codes/I21040Logic in AIhttps://scigraph.springernature.com/ontologies/product-market-codes/I21020Natural language processing (Computer science)Artificial intelligence.Computer logic.Natural Language Processing (NLP).Logic in AI.418.020285Cheng Yongauthttp://id.loc.gov/vocabulary/relators/aut781861BOOK9910349303003321Joint Training for Neural Machine Translation2537335UNINA01874oas 2200733 a 450 991013523970332120250921213016.01678-2674(OCoLC)46982304(CONSER) 2001252633(CKB)110978984562051(DE-599)ZDB2012156-8(EXLCZ)9911097898456205120010521a19989999 sy porurunu||||||||txtrdacontentcrdamediacrrdacarrierActa cirúrgica brasileira /publication of the Sociedade Brasileira para o Desenvolvimento da Pesquisa em CirurgiaSão Paulo, Brazil SOBRADPECRefereed/Peer-reviewed0102-8650 Acta cir. bras.Surgery, OperativePeriodicalsSurgical Procedures, OperativeSurgery, Operativefast(OCoLC)fst01139411Periodical.Periodicals.fastSurgery, OperativeSurgical Procedures, Operative.Surgery, Operative.Sociedade Brasileira para Desenvolvimento Pesquisa em CirurgiaWAUWAUOCLCQCGUOCLCQHEBISOCLCQOCLCFOCLCOOCLCQLIPXFHOCLCOOCLCQWY@OCLCOOCLCAAU@OCLCOWYUOCLCOOCLCAVT2OCLCQVXLHNCOCLCLJOURNAL9910135239703321Acta cirúrgica brasileira2191777UNINA