Journal: | Computación y Sistemas |
Database: | PERIÓDICA |
System number: | 000457496 |
ISSN: | 1405-5546 |
Authors: | Pandian, Arun1 Mulaffer, Lamana1 Oflazer, Kemal1 AlZeyara, Amna1 |
Institutions: | 1Carnegie Mellon University in Qatar, Doha City. Qatar |
Year: | 2020 |
Season: | Ene-Mar |
Volumen: | 24 |
Number: | 1 |
Pages: | 5-16 |
Country: | México |
Language: | Inglés |
Document type: | Artículo |
Approach: | Aplicado, descriptivo |
English abstract | 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 |
Disciplines: | Ciencias de la computación |
Keyword: | 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 |
Full text: | Texto completo (Ver HTML) Texto completo (Ver PDF) |