Litcius/Paper detail

Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity

Yang Zhao, Lu Xiang, Junnan Zhu, Jiajun Zhang, Zhou Yu, Chengqing Zong

202025 citationsDOIOpen Access PDF

Abstract

Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized. ii) Granularity mismatch: the current KG methods utilize the entity as the basic granularity, while NMT utilizes the sub-word as the granularity, making the KG different to be utilized in NMT.

Topics & Concepts

GranularityComputer scienceMachine translationSentenceNatural language processingTask (project management)Artificial intelligenceGraphKnowledge graphTranslation (biology)Machine learningTheoretical computer scienceProgramming languageBiochemistryEconomicsGeneManagementChemistryMessenger RNANatural Language Processing TechniquesTopic ModelingText Readability and Simplification
Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity | Litcius