FRCU - GIBD : Grupo de Investigación en Bases de Datos

Permanent URI for this communityhttp://48.217.138.120/handle/20.500.12272/774

Browse

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Técnicas de análisis de sentimientos aplicadas a la valoración de opiniones en el lenguaje español
    (2021-10-08) Rosenbrock, Germán; Trossero, Sebastián; Pascal, Andrés Jorge
    En el presente existen grandes cantidades de datos en formato de texto escritos en el lenguaje natural, disponibles principalmente en sitios web y redes sociales, que crece día a día. El análisis manual de estos volúmenes de información es actualmente impráctico y costoso, por lo cual se hace necesario el uso de técnicas automatizadas para su procesamiento y análisis. La Minería de Opinión o Análisis de Sentimientos estudia la extracción de información a partir de datos subjetivos y es relativamente reciente. En los últimos años se han propuesto varios modelos de procesamiento del lenguaje natural para resolver el problema particular de clasificación de sentimientos. En este trabajo examinamos el rendimiento de varios de estos modelos aplicados a un caso donde los textos están escritos en el lenguaje castellano coloquial, lo que representa un desafío adicional. El caso propuesto es un conjunto de más de 50.000 reseñas de películas, extraídas del sitio www.cinesargentinos.com.ar.
  • Thumbnail Image
    Item
    Intelligent chatter bot for regulation search
    (2016) López De Luise, María Daniela; Pascal, Andrés Jorge; Malgor, Rafael; Saad Correa, Ben Raúl; Pescio, Pablo; Carrilero, Patricio
    This communication presents a functional prototype implementing a linguistic model focused on regulations in Spanish. Its global architecture, the reasoning model and short statistics are provided for the prototype named PTAH. It mainly has a conversational robot linked to an Expert System by a module with many intelligent linguistic filters, implementing the reasoning model of an expert. It is focused in bylaws, regulations, jurisprudence and customized background representing entity mission, vision and profile. This Structure and model are generic enough to self-adapt to any regulatory environment, but as a first step, it was limited to academic field. This way it is possible to limit the slang and data number. The foundations of the linguistic model are also outlined and the way the architecture implements the key features of the behavior.
  • Thumbnail Image
    Item
    Chatterbot inteligente para asesoramiento jurídico
    (2016-06-15) López De Luise, María Daniela; Carrilero, Patricio; Pascal, Andrés Jorge; Malgor, Rafael; Alvarez, Claudia Mabel; Díaz, Joaquín; Pescio, Pablo; Saad Correa, Ben Raúl
    This paper presents the first results of a functional prototype implementing a linguistic model focused on regulations in Spanish. Its global architecture, the reasoning model, a case-study and short statistics are provided for the prototype named PTAH. It mainly has a conversational robot linked to an Expert System by a module with many intelligent linguistic filters, implementing the reasoning model of an expert. It is focused in bylaws, regulations, jurisprudence and customized background representing entity mission, vision and profile. This structure and model are generic enough to self adapt to any regulatory environment, but as a first step, it was limited to academic field. This way it is possible to limit the slang and data number. The foundations of the linguistic model and the way the architecture implements the key features of the behavior, are also outlined. The cases presented are a few just to show the usability, flexibility and prospectives of this proposal.