Neural Machine Translation
This is an educational resource for students and practitioners in machine translation, offering a structured overview without incremental research contributions.
The paper provides a comprehensive textbook chapter on neural machine translation, covering foundational concepts, the dominant attentional sequence-to-sequence model, and recent advancements, but does not present new research results or concrete numbers.
Draft of textbook chapter on neural machine translation. a comprehensive treatment of the topic, ranging from introduction to neural networks, computation graphs, description of the currently dominant attentional sequence-to-sequence model, recent refinements, alternative architectures and challenges. Written as chapter for the textbook Statistical Machine Translation. Used in the JHU Fall 2017 class on machine translation.