Content Word Aware Neural Machine Translation
Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita
Abstract
Neural machine translation (NMT) encodes the source sentence in a universal way to generate the target sentence word-byword. However, NMT does not consider the importance of word in the sentence meaning, for example, some words (i.e., content words) express more important meaning than others (i.e., function words).
Topics & Concepts
Computer scienceSentenceMachine translationNatural language processingTransformerWord (group theory)Artificial intelligenceGermanExample-based machine translationSpeech recognitionLinguisticsQuantum mechanicsPhilosophyPhysicsVoltageNatural Language Processing TechniquesTopic ModelingSemantic Web and Ontologies