Skip navigation
Please use this identifier to cite or link to this item: https://libeldoc.bsuir.by/handle/123456789/46657
Title: Developing a seq2seq neural network using visual attention to transform mathematical expressions from images to LaTeX
Authors: Vyaznikov, P. A.
Kotilevets, I. D.
Keywords: доклады БГУИР;im2latex;seq2seq;NLP;neural network
Issue Date: 2021
Publisher: БГУИР
Citation: Vyaznikov, P. A. Developing a seq2seq neural network using visual attention to transform mathematical expressions from images to LaTeX / Vyaznikov P. A., Kotilevets I. D. // Доклады БГУИР. – 2021. – № 19(8). – С. 40–44. – DOI : http://dx.doi.org/10.35596/1729-7648-2021-19-8-40-44.
Abstract: 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.
URI: https://libeldoc.bsuir.by/handle/123456789/46657
Appears in Collections:№ 19(8)

Files in This Item:
File Description SizeFormat 
Vyaznikov_Developing.pdf946.79 kBAdobe PDFView/Open
Show full item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.