Neural Monkey is a universal toolkit for training neural models for sequence-to-sequence tasks. The system has been successfully tested on machine translation, multimodal machine translation, or automatic post-editing. It can be used, however, for many other tasks, including image captioning, part-of-speech tagging, sequence classification, etc.
Neural Monkey's primary goal is to allow for fast prototyping and easy extension, which makes it a toolkit-of-choice for researchers who want to implement and/or modify recently published techniques.
Neural Monkey is written in Python 3 and built on the TensorFlow library. It supports training on GPUs with a minimum required effort.
Neural Monkey was used in the following publications:
The paper will hopefully be available soon. If you make use of Neural Monkey and are reading this notice, please send us an inquiry about how to cite.