Construction of Paraphrase Graphs as a Means of News Clusters Extraction

Autores/as

  • Elena Yagunova St.-Petersburg State University, Department of Informational Systems in Arts and Humanities, St.-Petersburg
  • Ekaterina Pronoza St.-Petersburg State University, Department of Informational Systems in Arts and Humanities, St.-Petersburg
  • Nataliya Kochetkova National Research University Higher School of Economics, School of Computer Engineering, St.-Petersburg

DOI:

https://doi.org/10.13053/cys-22-4-3065

Palabras clave:

News cluster, paraphrase graph, paraphrase extraction, linked text segments, text analysis

Resumen

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.

Descargas

Publicado

2018-12-30