Sequence to Sequence Learning with Neural Networks

Sutskever et al., 2014, Sequence to Sequence Learning with Neural Networks (Advances in Neural Information Processing Systems 27 (NIPS 2014))

Subscriber deck — free during early access

1 cards in “3.7 Performance on long sentences” · whole deck

3.7 Performance on long sentences

  1. How did seq2seq handle long sentences?
    Surprisingly well: there was no degradation for sentences under 35 words and only a minor drop for the longest, unlike earlier reports with similar models. Performance did drop on sentences with many rare words.

Source