Search Descriptions

Main Topics

Search Publications


author

title

other

year

Attention Model

The currently dominant model in neural machine translation is the sequence-to-sequence model with attention.

Attention Model is the main subject of 48 publications.

Publications

The attention model has its roots in a sequence-to-sequence model.

Cho et al. (2014) use recurrent neural networks for the approach. Sutskever et al. (2014) use a LSTM (long short-term memory) network and reverse the order of the source sentence before decoding.
The seminal work by Bahdanau et al. (2015) adds an alignment model (so called "attention mechanism") to link generated output words to source words, which includes conditioning on the hidden state that produced the preceding target word. Source words are represented by the two hidden states of recurrent neural networks that process the source sentence left-to-right and right-to-left. Luong et al. (2015) propose variants to the attention mechanism (which they call "global" attention model) and also a hard-constraint attention model ("local" attention model) which is restricted to a Gaussian distribution around a specific input word.
To explicitly model the trade-off between source context (the input words) and target context (the already produced target words), Tu et al. (2016) introduce an interpolation weight (called "context gate") that scales the impact of the (a) source context state and (b) the previous hidden state and the last word when predicting the next hidden state in the decoder.
Tu et al. (2017) augment the attention model with a reconstruction step. The generated output is translated back into the input language and the training objective is extended to not only include the likelihood of the target sentence but also the likelihood to the reconstructed input sentence.
Decoding: Freitag and Al-Onaizan (2017) introduce threshold pruning to neural machine translation. Discarding hypothesis whose score falls below a certain fraction of the best score are discarded, showing faster decoding while maintaining quality.

Benchmarks

Discussion

Related Topics

New Publications

Attention Model

  • Zhang et al. (2017)
  • Yu et al. (2016)
  • Alkhouli et al. (2016)
  • Huang et al. (2016)
  • Mi et al. (2016)
  • Calixto et al. (2017)
  • Press and Wolf (2017)
  • Yang et al. (2017)

Advanced Training

  • Zhang et al. (2016)
  • Stahlberg et al. (2017)
  • Yang et al. (2017)
  • Wiseman and Rush (2016)
  • Kreutzer et al. (2017)
  • Neubig (2016)
  • Cheng et al. (2016)
  • Shen et al. (2016)
  • Do et al. (2015)
  • Huang et al. (2015)
  • Cherry (2016)

Advanced Modelling

  • Zhou et al. (2016)
  • Gehring et al. (2017)
  • Oda et al. (2017)
  • Wang et al. (2017)
  • Tu et al. (2017)
  • Wang et al. (2016)
  • Sountsov and Sarawagi (2016)
  • Shu and Miura (2016)
  • Liu et al. (2016)

Decoding

  • Hu et al. (2015)
  • Mi et al. (2016)
  • Gu et al. (2017)
  • Hokamp and Liu (2017)
  • Zhou et al. (2017)
  • Zhou et al. (2017)
  • Shi and Knight (2017)
  • Kikuchi et al. (2016)
  • Hoang et al. (2017)
  • Ishiwatari et al. (2017)

Toolkits

  • Cromieres (2016)
  • Sennrich et al. (2017)
  • Klein et al. (2017)

Actions

Download

Contribute