“A novel approach to neural machine translation” by Facebook team shows a State-of-the-art results: https://code.facebook.com/posts/1978007565818999/a-novel-approach-to-neural-machine-translation/
Discussion: https://news.ycombinator.com/item?id=14301876
This approach is an alternative architecture for neural machine translation that opens up new possibilities for other text processing tasks. For example, multi-hop attention in dialogue systems allows neural networks to focus on distinct parts of the conversation, such as two separate facts, and to tie them together in order to better respond to complex questions.
References
[1] Convolutional Sequence to Sequence Learning. Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin.
[2] Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Łukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, Nishant Patil, Wei Wang, Cliff Young, Jason Smith, Jason Riesa, Alex Rudnick, Oriol Vinyals, Greg Corrado, Macduff Hughes, Jeffrey Dean. Technical Report, 2016.
[3] Neural Machine Translation by Jointly Learning to Align and Translate. Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio. International Conference on Learning Representations, 2015.
