КФУ. Карточка публикации. System for News Summarizing Using a Neural Network Algorithm

КАЗАНСКИЙ
ФЕДЕРАЛЬНЫЙ УНИВЕРСИТЕТ

RUS

- EN
- 中文
- ES

SYSTEM FOR NEWS SUMMARIZING USING A NEURAL NETWORK ALGORITHM

Форма представления

Статьи в зарубежных журналах и сборниках

Год публикации

2024

Язык

английский

Авторы, сотрудники КФУ

Ахмедова Альфира Мазитовна, автор

Библиографическое описание на языке оригинала

Akhmedova A, Zhazhneva I, Galimov G., System for News Summarizing Using a Neural Network Algorithm//RusAutoCon - Proceedings of the International Russian Automation Conference. - 2024. - Vol., Is.2024. - P.307-312.

Аннотация

RusAutoCon - Proceedings of the International Russian Automation Conference

Ключевые слова

text summarization, neural networks, Transformer architecture, mBart, telegram bot, news.

Название журнала

RusAutoCon - Proceedings of the International Russian Automation Conference

URL

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85208270528&doi=10.1109%2fRusAutoCon61949.2024.10694002&partnerID=40&md5=da3c218ddc1f5f755ef661383a0747b8

Пожалуйста, используйте этот идентификатор, чтобы цитировать или ссылаться на эту карточку

https://repository.kpfu.ru/?p_id=308521

Полная запись метаданных

Поле DC	Значение	Язык
dc.contributor.author	Ахмедова Альфира Мазитовна	ru_RU
dc.date.accessioned	2024-01-01T00:00:00Z	ru_RU
dc.date.available	2024-01-01T00:00:00Z	ru_RU
dc.date.issued	2024	ru_RU
dc.identifier.citation	Akhmedova A, Zhazhneva I, Galimov G., System for News Summarizing Using a Neural Network Algorithm//RusAutoCon - Proceedings of the International Russian Automation Conference. - 2024. - Vol., Is.2024. - P.307-312.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/?p_id=308521	ru_RU
dc.description.abstract	RusAutoCon - Proceedings of the International Russian Automation Conference	ru_RU
dc.description.abstract	This paper presents implementation of a system for summarizing news using a neural network algorithm. Relevance of the development of this system is due to the need for users to receive news in a concise form, while maintaining objectivity and accuracy of information transfer. Multilingual mBART Large CC25 model was chosen as the initial model. The main source of data for further training of the model was the gazeta dataset, taken from the Hugging Face project, supplemented by a collected data set from various news sources. To determine the qualities of the trained model, ROUGE and BLEU metrics were used. When developing the summarization algorithm, Python programming language with deep learning libraries PyTorch and Fairseq were used. The system works through the telegram bot interface. Telegram bot provides the ability to generate an annotation for the required news and produce the result in form of a message. The result of this work is a system that allows to receive a news summary in form of a short message.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	text summarization	ru_RU
dc.subject	neural networks	ru_RU
dc.subject	Transformer architecture	ru_RU
dc.subject	mBart	ru_RU
dc.subject	telegram bot	ru_RU
dc.subject	news.	ru_RU
dc.title	System for News Summarizing Using a Neural Network Algorithm	ru_RU
dc.type	Статьи в зарубежных журналах и сборниках	ru_RU