Revista: | Polibits |
Base de datos: | PERIÓDICA |
Número de sistema: | 000373732 |
ISSN: | 1870-9044 |
Autores: | Celebi, Arda1 Ozgur, Arzucan1 |
Instituciones: | 1Bogazici University, Department of Computer Engineering, Estambul. Turquía |
Año: | 2012 |
Periodo: | Jul-Dic |
Número: | 46 |
Paginación: | 5-12 |
País: | México |
Idioma: | Inglés |
Tipo de documento: | Artículo |
Enfoque: | Experimental, aplicado |
Resumen en inglés | Syntactic parsers are designed to detect the complete syntactic structure of grammatically correct sentences. In this paper, we introduce the concept of n-gram parsing, which corresponds to generating the constituency parse tree of n consecutive words in a sentence. We create a stand-alone n-gram parser derived from a baseline full discriminative constituency parser and analyze the characteristics of the generated n-gram trees for various values of n. Since the produced n-gram trees are in general smaller and less complex compared to full parse trees, it is likely that n-gram parsers are more robust compared to full parsers. Therefore, we use n-gram parsing to boost the accuracy of a full discriminative constituency parser in a hierarchical joint learning setup. Our results show that the full parser jointly trained with an n-gram parser performs statistically significantly better than our baseline full parser on the English Penn Treebank test corpus |
Disciplinas: | Ciencias de la computación |
Palabras clave: | Procesamiento de datos, Lingüística aplicada, Análisis gramatical, Aprendizaje discriminante, Aprendizaje de jerarquías conjuntas |
Keyword: | Computer science, Data processing, Applied linguistics, Parsing, Discriminant learning, Hierarchical joint learning |
Texto completo: | Texto completo (Ver HTML) |