Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
In 2016: stacked residual LSTMs with attention mechanisms on encoder/decoder are the best for NMT (Neural Machine Translation).
- from
- Education
- added
- 2026-10-10
- likes
- 0
similar
-
Neural Machine Translation by Jointly Learning to Align and Translate arxiv.org
Attention mechanism for LSTMs! Mostly, figures and formulas and their explanations revealed to be useful to me. I gave a talk on that paper here.
-
Massive Exploration of Neural Machine Translation Architectures arxiv.org
That yields intuition about the boundaries of what works for doing NMT within a framed seq2seq problem formulation.
-
Neural Machine Translation and Sequence-to-sequence Models: A Tutorial arxiv.org
Interesting overview of the subject of NMT, I mostly read part 8 about RNNs with attention as a refresher.
-
-
Neural Machine Translation cambridge.org
This introduction to machine translation starts from the basics of neural network methods and reaches the state of the art, while giving historical, linguistic, and applied context. Code examples in Python give a hands-on blueprint for implementation. The author is still…
-
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation arxiv.org
Two networks in one combined into a seq2seq (sequence to sequence) Encoder-Decoder architecture. RNN Encoder–Decoder with 1000 hidden units. Adadelta optimizer.
Education › Papers > Attention Mechanisms: “In 2016: stacked residual LSTMs with attention mechanisms on encoder/decoder are the best for NMT (Neural Machine Translation).”