Sílvia Moraes

Also published as: Silvia Moraes


2017

pdf bib
A study on irony within the context of 7x1-PT corpus
Silvia Moraes | Rackel Machado | Matheus Redecker | Rafael Cadaval | Felipe Meneguzzi
Proceedings of the 11th Brazilian Symposium in Information and Human Language Technology

pdf bib
Normalizador de Texto para Lingua Portuguesa baseado em Modelo de Linguagem (A Normalizer based on Language Model for Texts in Portuguese)[In Portuguese]
Patrick Bard | Renan Lopes Luis | Silvia Moraes
Proceedings of the 11th Brazilian Symposium in Information and Human Language Technology

2012

pdf bib
Combining Formal Concept Analysis and semantic information for building ontological structures from texts : an exploratory study
Sílvia Moraes | Vera Lima
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)

This work studies conceptual structures based on the Formal Concept Analysis method. We build these structures based on lexico-semantic information extracted from texts, among which we highlight the semantic roles. In our research, we propose ways to include semantic roles in concepts produced by this formal method. We analyze the contribution of semantic roles and verb classes in the composition of these concepts through structural measures. In these studies, we use the Penn Treebank Sample and SemLink 1.1 corpora, both in English.

2008

pdf bib
Keywords, k-NN and Neural Networks: a Support for Hierarchical Categorization of Texts in Brazilian Portuguese
Susana Azeredo | Silvia Moraes | Vera Lima
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

A frequent problem in automatic categorization applications involving Portuguese language is the absence of large corpora of previously classified documents, which permit the validation of experiments carried out. Generally, the available corpora are not classified or, when they are, they contain a very reduced number of documents. The general goal of this study is to contribute to the development of applications which aim at text categorization for Brazilian Portuguese. Specifically, we point out that keywords selection associated with neural networks can improve results in the categorization of Brazilian Portuguese texts. The corpus is composed of 30 thousand texts from the Folha de São Paulo newspaper, organized in 29 sections. In the process of categorization, the k-Nearest Neighbor (k-NN) algorithm and the Multilayer Perceptron neural networks trained with the backpropagation algorithm are used. It is also part of our study to test the identification of keywords parting from the log-likelihood statistical measure and to use them as features in the categorization process. The results clearly show that the precision is better when using neural networks than when using the k-NN.