ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Multilingual Graph Neural Network

Et Multilingual Graph Neural Network (Multilingual GNN) anvender graf-baseret besked-passage (message-passing) over knuder og kanter, der bærer træk fra to eller flere sprog. Det anvendes til opgaver som tværsproglig entitetsafstemning (cross-lingual entity alignment), tværsproglig fuldførelse af viden-grafer (multilingual knowledge-graph completion) og relations-ekstraktion på tværs af parallelle eller sammenlignelige korpora, hvilket muliggør fælles indlæring af strukturel og semantisk information fra flere sprog.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

The neighbourhood of related methods — select a node to explore.

Kilder

  1. Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR 2017. link
  2. Cao, Y., Liu, Z., Li, C., Li, J., & Chua, T.-S. (2019). Multi-channel graph neural network for entity alignment. In Proceedings of ACL 2019, 1452–1461. DOI: 10.18653/v1/P19-1140

Sådan citerer du denne side

ScholarGate. (2026, June 3). Multilingual Graph Neural Network. ScholarGate. https://scholargate.app/da/deep-learning/multilingual-graph-neural-network

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side
ScholarGateMultilingual graph neural network (Multilingual Graph Neural Network). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/multilingual-graph-neural-network · Datasæt: https://doi.org/10.5281/zenodo.20539026