FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093559770> ?p ?o ?g. }

• W3093559770 abstract "Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various architectures and analyses, the effectiveness of different context-aware NMT models is not well explored yet. This paper analyzes the performance of document-level NMT models on four diverse domains with a varied amount of parallel document-level bilingual data. We conduct a comprehensive set of experiments to investigate the impact of document-level NMT. We find that there is no single best approach to document-level NMT, but rather that different architectures come out on top on different tasks. Looking at task-specific problems, such as pronoun resolution or headline translation, we find improvements in the context-aware systems, even in cases where the corpus-level metrics like BLEU show no significant improvement. We also show that document-level back-translation significantly helps to compensate for the lack of document-level bi-texts." @default.
• W3093559770 created "2020-10-29" @default.
• W3093559770 creator A5010730319 @default.
• W3093559770 creator A5046577673 @default.
• W3093559770 creator A5047428600 @default.
• W3093559770 creator A5054692116 @default.
• W3093559770 creator A5056608595 @default.
• W3093559770 creator A5087367411 @default.
• W3093559770 date "2020-10-19" @default.
• W3093559770 modified "2023-09-27" @default.
• W3093559770 title "Diving Deep into Context-Aware Neural Machine Translation" @default.
• W3093559770 cites W131501223 @default.
• W3093559770 cites W1522301498 @default.
• W3093559770 cites W1738081185 @default.
• W3093559770 cites W2051840895 @default.
• W3093559770 cites W2067815623 @default.
• W3093559770 cites W2101105183 @default.
• W3093559770 cites W2151996595 @default.
• W3093559770 cites W2163038970 @default.
• W3093559770 cites W2574872930 @default.
• W3093559770 cites W2582446770 @default.
• W3093559770 cites W2606032440 @default.
• W3093559770 cites W2608029998 @default.
• W3093559770 cites W2626778328 @default.
• W3093559770 cites W2787560479 @default.
• W3093559770 cites W2799051177 @default.
• W3093559770 cites W2806987872 @default.
• W3093559770 cites W2888159079 @default.
• W3093559770 cites W2896457183 @default.
• W3093559770 cites W2902582221 @default.
• W3093559770 cites W2902614977 @default.
• W3093559770 cites W2923779212 @default.
• W3093559770 cites W2949888546 @default.
• W3093559770 cites W2952446148 @default.
• W3093559770 cites W2956301977 @default.
• W3093559770 cites W2962712961 @default.
• W3093559770 cites W2962784628 @default.
• W3093559770 cites W2962802109 @default.
• W3093559770 cites W2963216553 @default.
• W3093559770 cites W2963532001 @default.
• W3093559770 cites W2963842551 @default.
• W3093559770 cites W2964120396 @default.
• W3093559770 cites W2964289193 @default.
• W3093559770 cites W2964291396 @default.
• W3093559770 cites W2964308564 @default.
• W3093559770 cites W2971347700 @default.
• W3093559770 cites W3006381853 @default.
• W3093559770 cites W3018473580 @default.
• W3093559770 cites W3023598618 @default.
• W3093559770 cites W3045523169 @default.
• W3093559770 cites W3210914950 @default.
• W3093559770 hasPublicationYear "2020" @default.
• W3093559770 type Work @default.
• W3093559770 sameAs 3093559770 @default.
• W3093559770 citedByCount "1" @default.
• W3093559770 countsByYear W30935597702021 @default.
• W3093559770 crossrefType "posted-content" @default.
• W3093559770 hasAuthorship W3093559770A5010730319 @default.
• W3093559770 hasAuthorship W3093559770A5046577673 @default.
• W3093559770 hasAuthorship W3093559770A5047428600 @default.
• W3093559770 hasAuthorship W3093559770A5054692116 @default.
• W3093559770 hasAuthorship W3093559770A5056608595 @default.
• W3093559770 hasAuthorship W3093559770A5087367411 @default.
• W3093559770 hasConcept C104317684 @default.
• W3093559770 hasConcept C105580179 @default.
• W3093559770 hasConcept C119857082 @default.
• W3093559770 hasConcept C138885662 @default.
• W3093559770 hasConcept C149364088 @default.
• W3093559770 hasConcept C151730666 @default.
• W3093559770 hasConcept C154945302 @default.
• W3093559770 hasConcept C162324750 @default.
• W3093559770 hasConcept C177264268 @default.
• W3093559770 hasConcept C185592680 @default.
• W3093559770 hasConcept C187736073 @default.
• W3093559770 hasConcept C199360897 @default.
• W3093559770 hasConcept C203005215 @default.
• W3093559770 hasConcept C204321447 @default.
• W3093559770 hasConcept C23123220 @default.
• W3093559770 hasConcept C2778689934 @default.
• W3093559770 hasConcept C2779343474 @default.
• W3093559770 hasConcept C2780451532 @default.
• W3093559770 hasConcept C41008148 @default.
• W3093559770 hasConcept C41895202 @default.
• W3093559770 hasConcept C55493867 @default.
• W3093559770 hasConcept C86803240 @default.
• W3093559770 hasConceptScore W3093559770C104317684 @default.
• W3093559770 hasConceptScore W3093559770C105580179 @default.
• W3093559770 hasConceptScore W3093559770C119857082 @default.
• W3093559770 hasConceptScore W3093559770C138885662 @default.
• W3093559770 hasConceptScore W3093559770C149364088 @default.
• W3093559770 hasConceptScore W3093559770C151730666 @default.
• W3093559770 hasConceptScore W3093559770C154945302 @default.
• W3093559770 hasConceptScore W3093559770C162324750 @default.
• W3093559770 hasConceptScore W3093559770C177264268 @default.
• W3093559770 hasConceptScore W3093559770C185592680 @default.
• W3093559770 hasConceptScore W3093559770C187736073 @default.
• W3093559770 hasConceptScore W3093559770C199360897 @default.
• W3093559770 hasConceptScore W3093559770C203005215 @default.
• W3093559770 hasConceptScore W3093559770C204321447 @default.
• W3093559770 hasConceptScore W3093559770C23123220 @default.

• next