Utilização do modelo skip-gram para representação distribuída de palavras no projeto Media Cloud Brasil

• Ano de defesa: 2015
• Autor(a) principal: Lopes, Evandro Dalbem
• Orientador(a): Coelho, Flávio Codeço
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Palavras-chave em Português: Media Cloud Brasil; Processamento de linguagem natural; Redes neurais
• Palavras-chave em Inglês: Natural language processing; Neural networks; Skip-gram
• Link de acesso: http://hdl.handle.net/10438/16685

There is a representation problem when working with natural language processing because once the traditional model of bag-of-words represents the documents and words as single matrix, this one tends to be completely sparse. In order to deal with this problem, there are some methods capable of represent the words using a distributed representation, with a smaller dimension and more compact, including some properties that allow to relate words on the semantic form. The aim of this work is to use a dataset obtained by the Media Cloud Brasil project and apply the skip-gram model to explore relations and search for pattern that helps to understand the content.