| Инд. авторы: | Bakiyeva A.M., Batura T.V., Fedotov А.М. |
| Заглавие: | Methods and Systems of Automatic Text Summarization |
| Библ. ссылка: | Bakiyeva A.M., Batura T.V., Fedotov А.М. Methods and Systems of Automatic Text Summarization // Abstracts of the International Conference "Computational and Informational Technologies in Science, Ingenering and Education" (September 24-27, 2015) / Al-Farabi KazNU. - 2015. - Almaty: Al-Farabi KazNU. - P.50-50. - ISBN: 978-601-04-1389-4. |
| Реферат: | rus: The article discusses various methods for the problem of automatic text summarization, and provides an overview of systems which implementing these methods. Usually, allocate two approaches to automatic generation of a short essay (or annotations) text documents. The first involves the extraction of the most important pieces of text from one or more documents, the second is based on knowledge of the morphology, syntax and semantics of a particular language to generate concise reports. The most effective method is the semantic method that works as follows: the selected text is removed redundant information, superficial judgments, conceptual subgraphs. Next aggregation is performed and synthesis of information: the merger of some conceptual graphs based on the rules. The result is a conceptual squeeze. An important characteristic when choosing a method of abstracting is universal, ie, the method chosen must not impose restrictions on the theme and style of documents. |
| Издано: | 2015 |
| Физ. характеристика: | с.50-50 |
| Конференция: | Название: International Conference «Computational and Informational Technologies in Science, Engineering and Education» Аббревиатура: CITech-2015 Город: Алма-Ата Страна: Казахстан Даты проведения: 2015-09-24 - 2015-09-27 Ссылка: http://conf.nsc.ru/citech-2015 |
| Цитирование: | [1] Braslavskii P., Kolychev I. eXtragon: experimental system for automatic summarization of web documents // proceedings ROMIP. – 2005. – SPb. P. 40-53. [2] Barzilay R., Elhadad N., McKeown K. Inferring Strategies for Sentence Ordering in Multidocument News Summarization // Journal of Artificial Intelligence Research. Vol. 17.Is. 1. – 2002. P. 35-55. [3] Adwait Ratnaparkhi. Learning to parse natural language with maximum entropy mod-els[J] // Machine Learning. – 1999. 341(3). P. 151-176. [4] ”Manifold-Ranking Based Topic-Focused Multi-Document Summarization” DUC. – 2003. [5] J. Salton. Dynamic Library and Information Systems // Publishing house ”Mir” - 1979. P. 41-50. [6] Automatic text processing, http://aot.ru/ |