ScholarGate
Assistent
Process / pipeline

Maskinoversættelse

Maskinoversættelse (MT) er en naturlig-sprogsbehandlingsopgave, der automatisk konverterer tekst fra ét sprog til et andet. Moderne MT er baseret på neurale sekvens-til-sekvens-modeller – attention-mekanismen introduceret af Bahdanau et al. (2015) og transformer-arkitekturen af Vaswani et al. (2017) – og den udvider adgangen til kilder for flersproget dataanalyse og forskning.

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. Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. International Conference on Learning Representations (ICLR). link
  2. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. & Polosukhin, I. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems (NeurIPS). link

Sådan citerer du denne side

ScholarGate. (2026, June 1). Machine Translation. ScholarGate. https://scholargate.app/da/text-mining/machine-translation

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

Refereret af

ScholarGateMachine Translation (Machine Translation). Hentet 2026-06-15 fra https://scholargate.app/da/text-mining/machine-translation · Datasæt: https://doi.org/10.5281/zenodo.20539026