Made available in DSpace on 2016-04-29T14:23:42Z (GMT). No. of bitstreams: 1 Daniel Henrique da Silva.pdf: 3074984 bytes, checksum: 8157750ada0d1efd84ba9e3c3b73b64a (MD5) Previous issue date: 2015-12-11 / This research proposes a software architecture to the development of a tool for narrative scripts generation that follows the OCC-RDD technique. It is supposing that the choice of intelligent agents is adequate for this purpose, because of the diversity of inputs that make up a narrative script is propitious for artificial intelligence. In order to support the selection of the proposed architecture, a detailed study about OCC-RDD technique was made, followed by the use of a specific methodology for intelligent agents named TROPOS, in the analysis and solution design. There was also studies about theories and architectural styles suitable for software agents, as well as foundations and practices of software systems in general. The details of software architecture were designed with a prototype able to generate simple scripts which served to demonstrate the feasibility of the implementation. Some aspects of the text generation have been achieved by using a markup language built especially for this architecture. This language played the role of defining static text template in which intelligent agents consume to assemble the narrative script / A pesquisa propõe uma arquitetura de software para desenvolver uma ferramenta de geração de roteiros narrativos orientados a técnica OCC-RDD. Agentes inteligentes fo- ram escolhidos pela proximidade da área de estudo denomidada inteligência artificial que engloba a geração de roteiros narrativos. Para fundamentar a escolha da arquitetura pro- posta, foram feitos estudos detalhados sobre a técnica OCC-RDD, juntamente com o uso de uma metodologia específica para agentes inteligentes denominada TROPOS nas eta- pas de análise e de desenho da solução. Houve também estudos de teorias e de estilos arquiteturais apropriados para agentes, além de fundamentos e práticas de sistemas de software em geral. O detalhamento da arquitetura de software foi concebido junto com um protótipo capaz de gerar roteiros simples e que serviu para demonstrar a viabilidade da implementação. Alguns aspectos de geração de textos foram alcançados utilizando uma linguagem de marcação construída especialmente para esta arquitetura. Tal linguagem teve o papel importante de servir como uma definição de templates de texto estáticos no qual os agentes inteligentes a utilizam para montar o roteiro narrativo

Die vorliegende Dissertation analysiert Textgeneratoren aus der Frühzeit der Computergeschichte, seit den 1970er Jahren, ausgehend von ihrem Quelltext. Variablenskripte, Joseph Weizenbaums "Eliza", Kenneth Colbys "Parry", frühe Adventurespiele und Terry Winograds "SHRDLU" werden auf die ihnen zugrundelegienden metaphorischen und algorithmischen Strukturen untersucht. Alle diese Programme lassen sich auf den Glauben der formallogischen Tradition zurückführen, Sprache und das in ihr repräsentierte Wissen von Welt stellten vollständig explizierbare und sogar formalisierbare Sachverhalte dar, wie er in Ludwig Wittgensteins "Tractatus" kulminiert. Technisch werden hier optionale Elemente in Baumstrukturen angeordnet und erzeugen scheinbar unerschöpfliche Varianz. Dem wird eine zweite Traditionslinie gegenübergestellt, die statt an Optionen an Operationen arbeitet und mit dem Dadaisten Tristan Tzara, der Wiederentdeckung des russischen Mathematikers Andrei Markov durch Claude Shannon und den Cutup-Experimenten von William S. Burroughs verbunden ist. Als deren Weiterführung beschreibt die Arbeit das im Rahmen dieser Promotion entwickelte Computerprogramm "Poetry Machine", einen auf semantischen Netzwerken basierenden, interaktiven Textgenerator, der sich selbständig mit Informationen aus dem Internet versorgt. Im Anhang findet sich die Übersetzung des grundlegenden Textes "Ein Beispiel statistischer Forschung am Text ''Eugen Onegin'' zur Verbindung von Proben in Ketten" von A. Markov ins Deutsche. / The present dissertation analyses text generators from the early times of computer history, since the 1970ies, starting from their source code. Variable scripts, Joseph Weizenbaum''s "Eliza", Kenneth Colby''s "Parry", early adventure games and Terry Winograd''s "SHRDLU" are investigated regarding their metaphorical and arithmetical structure. These programs can be traced back to the belief of the formal-logic tradition that language and the knowledge about the world represented by it can be fully explained and even be formalised, like it culminates in Ludwig Wittgenstein''s "Tractatus". Technically, optional elements are arranged in tree-like structures and generate seemingly endless variance. A second line of tradition is opposed to this, that works on operations rather than on options. It is linked to the dadaist Tristan Tzara, the re-discovery of the Russian mathematician Andrei Markov by Claude Shannon and the cutup-experiments of William S. Burroughs. As a continuation, the computer program "Poetry Machine" is described in detail, which was developed within the framework of the present dissertation. This interactive text generator is based on semantic networks and acquires its information autonomously from the internet. The translation of the fundamental text "An Example of Statistical Investigation of the Text ''Eugene Onegin'' Concerning the Connection of Samples in Chains" by A. Markov into German is given in the appendix.