Image-to-Markup Generation with Coarse-to-Fine Attention

Yuntian Deng, Anssi Kanervisto, Jeffrey Ling, Alexander M. Rush
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:980-989, 2017.

Abstract

We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism. Our method is evaluated in the context of image-to-LaTeX generation, and we introduce a new dataset of real-world rendered mathematical expressions paired with LaTeX markup. We show that unlike neural OCR techniques using CTC-based models, attention-based approaches can tackle this non-standard OCR task. Our approach outperforms classical mathematical OCR systems by a large margin on in-domain rendered data, and, with pretraining, also performs well on out-of-domain handwritten data. To reduce the inference complexity associated with the attention-based approaches, we introduce a new coarse-to-fine attention layer that selects a support region before applying attention.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-deng17a, title = {Image-to-Markup Generation with Coarse-to-Fine Attention}, author = {Yuntian Deng and Anssi Kanervisto and Jeffrey Ling and Alexander M. Rush}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {980--989}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/deng17a/deng17a.pdf}, url = {https://proceedings.mlr.press/v70/deng17a.html}, abstract = {We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism. Our method is evaluated in the context of image-to-LaTeX generation, and we introduce a new dataset of real-world rendered mathematical expressions paired with LaTeX markup. We show that unlike neural OCR techniques using CTC-based models, attention-based approaches can tackle this non-standard OCR task. Our approach outperforms classical mathematical OCR systems by a large margin on in-domain rendered data, and, with pretraining, also performs well on out-of-domain handwritten data. To reduce the inference complexity associated with the attention-based approaches, we introduce a new coarse-to-fine attention layer that selects a support region before applying attention.} }
Endnote
%0 Conference Paper %T Image-to-Markup Generation with Coarse-to-Fine Attention %A Yuntian Deng %A Anssi Kanervisto %A Jeffrey Ling %A Alexander M. Rush %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-deng17a %I PMLR %P 980--989 %U https://proceedings.mlr.press/v70/deng17a.html %V 70 %X We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism. Our method is evaluated in the context of image-to-LaTeX generation, and we introduce a new dataset of real-world rendered mathematical expressions paired with LaTeX markup. We show that unlike neural OCR techniques using CTC-based models, attention-based approaches can tackle this non-standard OCR task. Our approach outperforms classical mathematical OCR systems by a large margin on in-domain rendered data, and, with pretraining, also performs well on out-of-domain handwritten data. To reduce the inference complexity associated with the attention-based approaches, we introduce a new coarse-to-fine attention layer that selects a support region before applying attention.
APA
Deng, Y., Kanervisto, A., Ling, J. & Rush, A.M.. (2017). Image-to-Markup Generation with Coarse-to-Fine Attention. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:980-989 Available from https://proceedings.mlr.press/v70/deng17a.html.

Related Material