Preview

Доклады БГУИР

Расширенный поиск

Developing a seq2seq neural network using visual attention to transform mathematical expressions from images to LaTeX

https://doi.org/10.35596/1729-7648-2021-19-8-40-44

Полный текст:

Аннотация

The paper presents the methods of development and the results of research on the effectiveness of the seq2seq neural network architecture using Visual Attention mechanism to solve the im2latex problem. The essence of the task is to create a neural network capable of converting an image with mathematical expressions into a similar expression in the LaTeX markup language. This problem belongs to the Image Captioning type: the neural network scans the image and, based on the extracted features, generates a description in natural language. The proposed solution uses the seq2seq architecture, which contains the Encoder and Decoder mechanisms, as well as Bahdanau Attention. A series of experiments was conducted on training and measuring the effectiveness of several neural network models.

Ключевые слова


Об авторах

P А. Vyaznikov
MIREA – Russian Technological University
Россия


I D. Kotilevets
MIREA – Russian Technological University
Россия


Список литературы

1. Hochreiter S., Schmidhuber J. Long Short-Term Memory. Neural Computation. 1997;9(8):1735-1780.

2. Bahdanau D., Cho K., Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate. 3rd International Conference on Learning Representations, ICLR 2015.

3. Papineni K., Roukos S., Ward T., Zhu W. BLEU: a method for automatic evaluation of machine translation. ACL '02: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, 2002: 311-318.


Рецензия

Для цитирования:


Vyaznikov P.А., Kotilevets I.D. Developing a seq2seq neural network using visual attention to transform mathematical expressions from images to LaTeX. Доклады БГУИР. 2021;19(8):40-44. https://doi.org/10.35596/1729-7648-2021-19-8-40-44

For citation:


Vyaznikov P.A., Kotilevets I.D. Developing a seq2seq neural network using visual attention to transform mathematical expressions from images to LaTeX. Doklady BGUIR. 2021;19(8):40-44. https://doi.org/10.35596/1729-7648-2021-19-8-40-44

Просмотров: 46


Creative Commons License
Контент доступен под лицензией Creative Commons Attribution 4.0 License.


ISSN 1729-7648 (Print)
ISSN 2708-0382 (Online)