Revista: | Computación y Sistemas |
Base de datos: | PERIÓDICA |
Número de sistema: | 000457496 |
ISSN: | 1405-5546 |
Autores: | Pandian, Arun1 Mulaffer, Lamana1 Oflazer, Kemal1 AlZeyara, Amna1 |
Instituciones: | 1Carnegie Mellon University in Qatar, Doha City. Qatar |
Año: | 2020 |
Periodo: | Ene-Mar |
Volumen: | 24 |
Número: | 1 |
Paginación: | 5-16 |
País: | México |
Idioma: | Inglés |
Tipo de documento: | Artículo |
Enfoque: | Aplicado, descriptivo |
Resumen en inglés | This paper presents a neural network classifier approach to detecting precise within-document(WD) and cross-document(CD) event coreference clusters effectively using only event mention based features. Our approach does not rely on any event argument features such as semantic roles or spatio-temporal arguments and uses no sophisticated clustering approach. Experimental results on the ECB+ dataset show that our simple approach outperforms state-of-the-art methods for both within-document and cross-document event coreference resolution while producing clusters of high precision, which is useful for several downstream tasks |
Disciplinas: | Ciencias de la computación |
Palabras clave: | Inteligencia artificial, Procesamiento de datos, Programación, Aprendizaje profundo, Clasificación de documentos, Eventos, Semántica, Redes neuronales |
Keyword: | Artificial intelligence, Data processing, Programming, Deep learning, Document classification, Events, Semantics, Neural networks |
Texto completo: | Texto completo (Ver HTML) Texto completo (Ver PDF) |