neural machine translation

A translation approach that uses neural networks to map a source sentence to a target sentence.

• Types

  method

• Aliases

  NMT

• Contributors
  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) review

• On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

  7,342 citations

• Neural machine translation performs relatively well on short sentences without unknown words.
• Performance degrades rapidly as sentence length increases and as the number of unknown words increases.
• RNN Encoder--Decoder and a newly proposed gated recursive convolutional neural network are the two models analyzed for neural machine translation properties.

• neural machine translation

  related toIncomingmethod

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

• short sentences

  input category1 shared papers
• unknown words

  linguistic feature1 shared papers
• sentence length

  feature1 shared papers
• gated recursive convolutional neural network

  model1 shared papers
• grammatical structure

  linguistic property1 shared papers
• rnn encoder--decoder

  model1 shared papers