FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899427634> ?p ?o ?g. }

• W2899427634 abstract "Generative Adversarial Network (GAN) has been proposed to tackle the exposure bias problem of Neural Machine Translation (NMT). However, the discriminator typically results in the instability of the GAN training due to the inadequate training problem: the search space is so huge that sampled translations are not sufficient for discriminator training. To address this issue and stabilize the GAN training, in this paper, we propose a novel Bidirectional Generative Adversarial Network for Neural Machine Translation (BGAN-NMT), which aims to introduce a generator model to act as the discriminator, whereby the discriminator naturally considers the entire translation space so that the inadequate training problem can be alleviated. To satisfy this property, generator and discriminator are both designed to model the joint probability of sentence pairs, with the difference that, the generator decomposes the joint probability with a source language model and a source-to-target translation model, while the discriminator is formulated as a target language model and a target-to-source translation model. To further leverage the symmetry of them, an auxiliary GAN is introduced and adopts generator and discriminator models of original one as its own discriminator and generator respectively. Two GANs are alternately trained to update the parameters. Experiment results on German-English and Chinese-English translation tasks demonstrate that our method not only stabilizes GAN training but also achieves significant improvements over baseline systems." @default.
• W2899427634 created "2018-11-09" @default.
• W2899427634 creator A5028604823 @default.
• W2899427634 creator A5034770439 @default.
• W2899427634 creator A5048237545 @default.
• W2899427634 creator A5049732922 @default.
• W2899427634 creator A5051065845 @default.
• W2899427634 date "2018-01-01" @default.
• W2899427634 modified "2023-10-18" @default.
• W2899427634 title "Bidirectional Generative Adversarial Networks for Neural Machine Translation" @default.
• W2899427634 cites W1533861849 @default.
• W2899427634 cites W2064675550 @default.
• W2899427634 cites W2099471712 @default.
• W2899427634 cites W2101105183 @default.
• W2899427634 cites W2118434577 @default.
• W2899427634 cites W2130942839 @default.
• W2899427634 cites W2153653739 @default.
• W2899427634 cites W2157331557 @default.
• W2899427634 cites W2173520492 @default.
• W2899427634 cites W2437005631 @default.
• W2899427634 cites W2542835211 @default.
• W2899427634 cites W2546938941 @default.
• W2899427634 cites W2577946330 @default.
• W2899427634 cites W2581637843 @default.
• W2899427634 cites W2601324753 @default.
• W2899427634 cites W2618606525 @default.
• W2899427634 cites W2794365787 @default.
• W2899427634 cites W2962824887 @default.
• W2899427634 cites W2963163972 @default.
• W2899427634 cites W2963206679 @default.
• W2899427634 cites W2963216553 @default.
• W2899427634 cites W2963248296 @default.
• W2899427634 cites W2963403868 @default.
• W2899427634 cites W2963463964 @default.
• W2899427634 cites W2963551569 @default.
• W2899427634 cites W2963620441 @default.
• W2899427634 cites W2964265128 @default.
• W2899427634 cites W2964268978 @default.
• W2899427634 cites W2964308564 @default.
• W2899427634 cites W648786980 @default.
• W2899427634 doi "https://doi.org/10.18653/v1/k18-1019" @default.
• W2899427634 hasPublicationYear "2018" @default.
• W2899427634 type Work @default.
• W2899427634 sameAs 2899427634 @default.
• W2899427634 citedByCount "15" @default.
• W2899427634 countsByYear W28994276342020 @default.
• W2899427634 countsByYear W28994276342021 @default.
• W2899427634 countsByYear W28994276342022 @default.
• W2899427634 countsByYear W28994276342023 @default.
• W2899427634 crossrefType "proceedings-article" @default.
• W2899427634 hasAuthorship W2899427634A5028604823 @default.
• W2899427634 hasAuthorship W2899427634A5034770439 @default.
• W2899427634 hasAuthorship W2899427634A5048237545 @default.
• W2899427634 hasAuthorship W2899427634A5049732922 @default.
• W2899427634 hasAuthorship W2899427634A5051065845 @default.
• W2899427634 hasBestOaLocation W28994276341 @default.
• W2899427634 hasConcept C104317684 @default.
• W2899427634 hasConcept C105580179 @default.
• W2899427634 hasConcept C121332964 @default.
• W2899427634 hasConcept C137293760 @default.
• W2899427634 hasConcept C149364088 @default.
• W2899427634 hasConcept C153083717 @default.
• W2899427634 hasConcept C154945302 @default.
• W2899427634 hasConcept C163258240 @default.
• W2899427634 hasConcept C185592680 @default.
• W2899427634 hasConcept C203005215 @default.
• W2899427634 hasConcept C2777530160 @default.
• W2899427634 hasConcept C2779803651 @default.
• W2899427634 hasConcept C2780992000 @default.
• W2899427634 hasConcept C28490314 @default.
• W2899427634 hasConcept C39890363 @default.
• W2899427634 hasConcept C41008148 @default.
• W2899427634 hasConcept C50644808 @default.
• W2899427634 hasConcept C55493867 @default.
• W2899427634 hasConcept C62520636 @default.
• W2899427634 hasConcept C76155785 @default.
• W2899427634 hasConcept C94915269 @default.
• W2899427634 hasConceptScore W2899427634C104317684 @default.
• W2899427634 hasConceptScore W2899427634C105580179 @default.
• W2899427634 hasConceptScore W2899427634C121332964 @default.
• W2899427634 hasConceptScore W2899427634C137293760 @default.
• W2899427634 hasConceptScore W2899427634C149364088 @default.
• W2899427634 hasConceptScore W2899427634C153083717 @default.
• W2899427634 hasConceptScore W2899427634C154945302 @default.
• W2899427634 hasConceptScore W2899427634C163258240 @default.
• W2899427634 hasConceptScore W2899427634C185592680 @default.
• W2899427634 hasConceptScore W2899427634C203005215 @default.
• W2899427634 hasConceptScore W2899427634C2777530160 @default.
• W2899427634 hasConceptScore W2899427634C2779803651 @default.
• W2899427634 hasConceptScore W2899427634C2780992000 @default.
• W2899427634 hasConceptScore W2899427634C28490314 @default.
• W2899427634 hasConceptScore W2899427634C39890363 @default.
• W2899427634 hasConceptScore W2899427634C41008148 @default.
• W2899427634 hasConceptScore W2899427634C50644808 @default.
• W2899427634 hasConceptScore W2899427634C55493867 @default.
• W2899427634 hasConceptScore W2899427634C62520636 @default.
• W2899427634 hasConceptScore W2899427634C76155785 @default.
• W2899427634 hasConceptScore W2899427634C94915269 @default.
• W2899427634 hasLocation W28994276341 @default.
• W2899427634 hasOpenAccess W2899427634 @default.

• next