CS224D Final Report: Deep Recurrent Attention Networks for LATEX to Source

For our project, we wanted to explore the problem of recognizing LTEX expressions and translating them to source using a deep neural network. Previous work involving attention models have improved sequence to sequence mappings and greatly helped in digit recognition. Inspired by these previous work, we implemented an attention model to recognize simple LTEX expressions and also tested it on a small subset of CROHME, a dataset of handwritten mathematical expressions. We thoroughly explain our network, training procedure, hyperparameter tuning, and results. We achieve a classification accuracy of 63.4% on an automatically generated dataset and an accuracy of XXXXXX on CROHME.