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 “3.3 Reversing the Source Sentences” · whole deck
3.3 Reversing the Source Sentences
- How much did reversing source sentences improve seq2seq?Test perplexity dropped from 5.8 to 4.7 and BLEU of decoded translations rose from 25.9 to 30.6. Unexpectedly, it also made long sentences translate much better, suggesting better memory utilization, not just more confident early predictions.
- Sutskever et al., 2014, Sequence to Sequence Learning with Neural Networks (Advances in Neural Information Processing Systems 27 (NIPS 2014)), §3.3
Source
- Ilya Sutskever, Oriol Vinyals and Quoc V. Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems 27 (NIPS 2014). https://papers.nips.cc/paper/2014/hash/5a18e133cbf9f257297f410bb7eca942-Abstract.html