Revista: | Computación y sistemas |
Base de datos: | |
Número de sistema: | 000560409 |
ISSN: | 1405-5546 |
Autores: | Yagunova, Elena1 Pronoza, Ekaterina1 Kochetkova, Nataliya2 |
Instituciones: | 1St.-Petersburg State University, Department of Informational Systems in Arts and Humanities, St-Petersburg. Rusia 2National Research University Higher School of Economics, School of Computer Engineering, St-Petersburg. Rusia |
Año: | 2018 |
Periodo: | Oct-Dic |
Volumen: | 22 |
Número: | 4 |
Paginación: | 1329-1336 |
País: | México |
Idioma: | Inglés |
Tipo de documento: | Artículo |
Resumen en inglés | In this paper, we construct paraphrase graphs for news text collections (clusters). Our aims are, first, to prove that paraphrase graph construction method can be used for news clusters identification and, second, to analyze and compare stylistically different news collections. Our news collections include dynamic, static and combined (dynamic and static) texts. Their respective paraphrase graphs reflect their main characteristics. We also automatically extract the most informationally important linked fragments of news texts, and these fragments characterize news texts as either informative, conveying some information, or publicistic ones, trying to affect the readers emotionally. |
Disciplinas: | Ciencias de la computación |
Palabras clave: | Inteligencia artificial |
Keyword: | News cluster, Paraphrase graph, Paraphrase extraction, Linked text segments, Text analysis, Artificial intelligence |
Texto completo: | Texto completo (Ver HTML) Texto completo (Ver PDF) |