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 “3.6 Experimental Results” · whole deck
3.6 Experimental Results
- Why was the seq2seq result a landmark even though it didn’t beat the state of the art?It was the first time a pure neural translation system beat a phrase-based SMT baseline on a large MT task by a sizeable margin, despite being relatively unoptimized and unable to handle out-of-vocabulary words.
- Sutskever et al., 2014, Sequence to Sequence Learning with Neural Networks (Advances in Neural Information Processing Systems 27 (NIPS 2014)), §3.6
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