| Journal: | Polibits |
| Database: | PERIÓDICA |
| System number: | 000373732 |
| ISSN: | 1870-9044 |
| Authors: | Celebi, Arda1 Ozgur, Arzucan1 |
| Institutions: | 1Bogazici University, Department of Computer Engineering, Estambul. Turquía |
| Year: | 2012 |
| Season: | Jul-Dic |
| Number: | 46 |
| Pages: | 5-12 |
| Country: | México |
| Language: | Inglés |
| Document type: | Artículo |
| Approach: | Experimental, aplicado |
| English abstract | 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 |
| Disciplines: | Ciencias de la computación |
| Keyword: | 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 |
| Full text: | Texto completo (Ver HTML) |
