Can I read Translating Math Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training on EtoBox?

Translating Math Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training by Wang, Zelun; Liu, Jyh-Charn is a scholarly article available to read on EtoBox.

What is Translating Math Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training about?

In this paper we propose a deep neural network model with an encoder-decoder architecture that translates images of math formulas into their LaTeX markup sequences. The encoder is a convolutional neural network (CNN) that transforms images into a group of feature maps. To better capture the spatial relationships of math symbols, the feature maps are augmented with 2D positional encoding before being unfolded into a vector. The decoder is a stacked bidirectional long short-term memory (LSTM) model integrated with the soft attention mechanism, which works as a language model to translate the encoder output into a sequence of LaTeX tokens. The neural network is trained in two steps. The first step is token-level training using the Maximum-Likelihood Estimation (MLE) as the objective function. At completion of the token-level training, the sequence-level training objective function is employed to optimize the overall model based on the policy gradient algorithm from reinforcement learning. Our design also overcomes the exposure bias problem by closing the feedback loop in the decoder during sequence-level training, i.e., feeding in the predicted token instead of the ground truth token

Author

Wang, Zelun; Liu, Jyh-Charn

Published

2019

Language

EN