Projects

These are some of the open-source projects I work on to make neural text generation technologies more readily available for developers and researchers.

Cascaded Text Generation with Markov Transformers
A parallel, fast, autoregressive, and accurate text generation algorithm using high-order Conditional Random Fields (CRFs).
github
Break Through AI
Break Through AI is a free summer program for supporting female undergraduates to learn AI and ML skills in an applied environment. I helped prepare some materials for a summer course my advisor Sasha taught (https://github.com/srush/BT-AI).
github
Neural Linguistic Steganography
A practical linguistic steganography algorithm via arithmetic coding and strong neural models.
github
OpenNMT
A full service open-source neural machine translation system. Originally developed in Lua with Systran, since ported to PyTorch and TensorFlow and maintained externally.
github
Image-to-Markup
A general-purpose, deep learning-based system to decompile an image into presentational markup. For example, we can infer the LaTeX or HTML source from a rendered image.
github
Attention OCR
A deep learning-based optical character recognition (OCR) system implemented in TensorFlow.
github