Towards Russian Text Generation Problem Using  OpenAI’s GPT-2

Shatalov, O.; Ryabova, N. V.

Публікація:
Towards Russian Text Generation Problem Using OpenAI’s GPT-2

dc.contributor.author	Shatalov, O.
dc.contributor.author	Ryabova, N. V.
dc.date.accessioned	2022-01-11T11:27:09Z
dc.date.available	2022-01-11T11:27:09Z
dc.date.issued	2021
dc.description.abstract	This work is devoted to Natural Language Generation (NLG) problem. The modern approaches in this area based on deep neural networks are considered. The most famous and promising deep neural network architectures that are related to this problem are considered, in particular, the most popular free software solutions for NLG based on Transformers architecture with pre-trained deep neural network models GPT-2 and BERT. The main problem is that the main part of already existing solutions is devoted to the English language. But there are few models that are able to generate text in Russian. Moreover, the text they generate often belongs to a general topic and not about a specific subject area. The object of the study is the generation of a contextually coherent narrow-profile text in Russian. Within the framework of the study, a model was trained for generating coherent articles of a given subject area in Russian, as well as a software application for interacting with it.	uk_UA
dc.identifier.citation	Shatalov O., Ryabova N. Towards Russian Text Generation Problem Using OpenAI’s GPT-2. Proc. 5th Int. Conf. On Computational Linguistics and Intelligent Systems (COLINS), Volume I: Main Conference. CEUR Workshop Proceedings, 2021, 2870, pp.141-153.	uk_UA
dc.identifier.uri	URN: urn:nbn:de:0074-2870-3
dc.identifier.uri	ARCHIVE: http://sunsite.informatik.rwth-aachen.de/ftp/pub/publications/CEUR-WS/Vol-2870.zip
dc.identifier.uri	https://openarchive.nure.ua/handle/document/19040
dc.language.iso	en	uk_UA
dc.publisher	CEUR Workshop Proceedings	uk_UA
dc.relation.ispartofseries	Volume 2870;pp.141-153
dc.subject	Natural Language Generation	uk_UA
dc.subject	Natural Language Processingч	uk_UA
dc.subject	Transformers Architecture	uk_UA
dc.subject	Deep Learning	uk_UA
dc.subject	Transfer Learning	uk_UA
dc.subject	GPT-2	uk_UA
dc.title	Towards Russian Text Generation Problem Using OpenAI’s GPT-2	uk_UA
dc.title.alternative	Proc. 5th Int. Conf. On Computational Linguistics and Intelligent Systems (COLINS), Volume I: Main Conference.	uk_UA
dc.type	Conference proceedings	uk_UA
dspace.entity.type	Publication