这篇论文来自Yoshua Bengio的实验室，而标题并不起眼「Neural Machine Translation by Jointly Learning to Align and Translate」。 或许很多人都没有听说过这篇论文，但它是NLP中最伟大的里程碑之一，已经被引用了29K次（相比之下，Transformer为77K）。

Computer vision continues to be one of the most dynamic and impactful fields in artificial intelligence. Thanks to breakthroughs in deep learning, architecture design and data efficiency, machines are ...