neural machine translation

A machine translation approach that uses a single neural network to model translation from source to target.

• Types

  method

• Aliases

  No aliases are listed.

• Contributors
  뀨 (7c402c1b98) extractionAnonymous (12632b8b5f) review

• Neural Machine Translation by Jointly Learning to Align and Translate

  29,013 citations

• A neural machine translation model is proposed that jointly learns to align and translate by replacing the fixed-length vector bottleneck in the basic encoder-decoder architecture with a soft alignment mechanism.
• On English-to-French translation, the proposed model achieves performance comparable to the existing state-of-the-art phrase-based machine translation system.

• neural machine translation

  related toOutgoingmethod

  Both neural machine translation concepts describe the same neural-network-based translation approach that maps a source sentence to a target sentence.

• encoder-decoder architecture

  architecture1 shared papers
• fixed-length vector

  representation1 shared papers
• soft alignment

  mechanism1 shared papers
• phrase-based machine translation system

  baseline, system1 shared papers
• english-to-french translation

  task1 shared papers