Revue: | Computación y sistemas |
Base de datos: | PERIÓDICA |
Número de sistema: | 000410219 |
ISSN: | 1405-5546 |
Autores: | Toldova, Svetlana1 lonov, Max2 |
Instituciones: | 1National Research Institute "Higher School of Economics", Moscú. Rusia 2Moscow State University, Rusia |
Año: | 2016 |
Periodo: | Oct-Dic |
Volumen: | 20 |
Número: | 4 |
Paginación: | 681-696 |
País: | México |
Idioma: | Inglés |
Tipo de documento: | Artículo |
Enfoque: | Experimental, aplicado |
Resumen en inglés | Coreference resolution task is a well-known NLP application that was proven helpful for all high-level NLP applications: machine translation, summarization, and others. Mention detection is the sub-task of detecting the discourse status of each noun phrase, classifying it as a discourse-new, singleton (mentioned only once) or discourse-old occurrence. It has been shown that this task applied to a coreference resolution system may increase its overall performance. So, we decided to adapt current approaches for English language into Russian. We present some quality results of experiments regarding classifiers for mention detection and their application into the coreference resolution task in Russian languages |
Disciplinas: | Ciencias de la computación, Literatura y lingüística |
Palabras clave: | Procesamiento de datos, Lingüística aplicada, Procesamiento del discurso, Procesamiento de lenguaje natural, Aprendizaje de máquinas, Correferencias |
Keyword: | Computer science, Literature and linguistics, Data processing, Applied linguistics, Discourse processing, Natural language processing, Machine learning, Coreferences |
Texte intégral: | Texto completo (Ver HTML) |