| Grant number: | 14/20830-0 |
| Support Opportunities: | Regular Research Grants |
| Start date: | February 01, 2015 |
| End date: | January 31, 2017 |
| Field of knowledge: | Physical Sciences and Mathematics - Computer Science |
| Principal Investigator: | Diego Raphael Amancio |
| Grantee: | Diego Raphael Amancio |
| Host Institution: | Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil |
Abstract
Complex networks (CN) have been widely employed to model texts. Although some theoretical results have investigated the structural and functional properties of the language via the CN framework, the applicability of the topological analysis of CNs to solve linguistic problems have been restricted to a few studies. The proposed project aims at improving current CN-based models modeling traditional and novel applications. More specifically, we propose the combination of traditional and CN-based techniques based on time series analysis in order to improve the performance of natural language processing tasks, such as the authorship recognition and the disambiguation problems. Upon combining traditional and CN-based techniques in a hybrid way, we expect to generate competitive unsupervised and supervised classifiers. We also expect that the generated models will provide relevant insights into the language functional mechanisms. (AU)
| Articles published in Agência FAPESP Newsletter about the research grant: |
| More itemsLess items |
| TITULO |
| Articles published in other media outlets ( ): |
| More itemsLess items |
| VEICULO: TITULO (DATA) |
| VEICULO: TITULO (DATA) |