Este libro es fruto de una labor que abreva en diferentes perspectivas teórico-metodológicas para... more Este libro es fruto de una labor que abreva en diferentes perspectivas teórico-metodológicas para intentar dar cuenta de la complejidad que encierra el tratamiento de diferentes temas relacionados directamente con la pobreza en la prensa latinoamericana. Todos sus artículos son fruto de un estudio realizado a partir del corpus PoLaMe, conformado por textos periodísticos que abordan la pobreza en Argentina, Brasil, Colombia y México. Desde el análisis del vínculo entre derechos humanos y pobreza, pasando por las ideologías que subyacen a los discursos sobre la cuestión, hasta trabajos producidos desde la lingüística; este volumen intenta sumar perspectivas para analizar un fenómeno que constituye, tal vez, el problema más importante de América Latina
High frequency can convert a word sequence into a multiword expression (MWE), i.e., a collocation... more High frequency can convert a word sequence into a multiword expression (MWE), i.e., a collocation. In this paper, we use collocations as well as syntactically-flexible, lexicalized phrases to analyze ‘job specification documents’ (a kind of corporate technical document) for subsequent acquisition of automated knowledge elicitation. We propose the definition of structural and functional patterns of specific corporate documents by analyzing the contexts and sections in which the expression occurs. Such patterns and its automated processing are the basis for identifying organizational domain knowledge and business information which is used later for the first instances of requirement elicitation processes in software engineering.
The automatic prediction of the course of action of agents involved in social or economic trends ... more The automatic prediction of the course of action of agents involved in social or economic trends is an imperative challenge nowadays. However, it is a difficult task because stance or opinion is often spread throughout long, complex texts, such as news articles. The current study tests sentence predicates as features to automatically determine the writer’s stance in news articles. We capture the semantics and stance of the text by encoding features such as the attribute of copulative sentences, the predicate of transitive sentences, adjectival phrases, and the section of the article. Under the assumption that these features are informative enough to model the semantics of the text, each word sequence is disambiguated and assigned a sentiment value using weighting rules. Different experiments were run using either SentiWordNet and ML-Senticon to determine words’ sentiment. Feature vectors are automatically built to populate a database that is tested using two machine learning algorit...
Proceedings of the Naacl Hlt 2010 Young Investigators Workshop on Computational Approaches to Languages of the Americas, Jun 6, 2010
Page 88. Proceedings of the NAACL HLT 2010 Young Investigators Workshop on Computational Approach... more Page 88. Proceedings of the NAACL HLT 2010 Young Investigators Workshop on Computational Approaches to Languages of the Americas, pages 7683, Los Angeles, California, June 2010. cO2010 Association for Computational ...
Este libro es fruto de una labor que abreva en diferentes perspectivas teórico-metodológicas para... more Este libro es fruto de una labor que abreva en diferentes perspectivas teórico-metodológicas para intentar dar cuenta de la complejidad que encierra el tratamiento de diferentes temas relacionados directamente con la pobreza en la prensa latinoamericana. Todos sus artículos son fruto de un estudio realizado a partir del corpus PoLaMe, conformado por textos periodísticos que abordan la pobreza en Argentina, Brasil, Colombia y México. Desde el análisis del vínculo entre derechos humanos y pobreza, pasando por las ideologías que subyacen a los discursos sobre la cuestión, hasta trabajos producidos desde la lingüística; este volumen intenta sumar perspectivas para analizar un fenómeno que constituye, tal vez, el problema más importante de América Latina
High frequency can convert a word sequence into a multiword expression (MWE), i.e., a collocation... more High frequency can convert a word sequence into a multiword expression (MWE), i.e., a collocation. In this paper, we use collocations as well as syntactically-flexible, lexicalized phrases to analyze ‘job specification documents’ (a kind of corporate technical document) for subsequent acquisition of automated knowledge elicitation. We propose the definition of structural and functional patterns of specific corporate documents by analyzing the contexts and sections in which the expression occurs. Such patterns and its automated processing are the basis for identifying organizational domain knowledge and business information which is used later for the first instances of requirement elicitation processes in software engineering.
The automatic prediction of the course of action of agents involved in social or economic trends ... more The automatic prediction of the course of action of agents involved in social or economic trends is an imperative challenge nowadays. However, it is a difficult task because stance or opinion is often spread throughout long, complex texts, such as news articles. The current study tests sentence predicates as features to automatically determine the writer’s stance in news articles. We capture the semantics and stance of the text by encoding features such as the attribute of copulative sentences, the predicate of transitive sentences, adjectival phrases, and the section of the article. Under the assumption that these features are informative enough to model the semantics of the text, each word sequence is disambiguated and assigned a sentiment value using weighting rules. Different experiments were run using either SentiWordNet and ML-Senticon to determine words’ sentiment. Feature vectors are automatically built to populate a database that is tested using two machine learning algorit...
Proceedings of the Naacl Hlt 2010 Young Investigators Workshop on Computational Approaches to Languages of the Americas, Jun 6, 2010
Page 88. Proceedings of the NAACL HLT 2010 Young Investigators Workshop on Computational Approach... more Page 88. Proceedings of the NAACL HLT 2010 Young Investigators Workshop on Computational Approaches to Languages of the Americas, pages 7683, Los Angeles, California, June 2010. cO2010 Association for Computational ...
Uploads
Papers by Diego Burgos