Made available in DSpace on 2014-06-12T15:54:30Z (GMT). No. of bitstreams: 2 arquivo7155_1.pdf: 666963 bytes, checksum: 56eeb6eb903215d0a8b285686ffe780a (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 2005 / O trabalho de pesquisa aqui apresentado teve como objetivo principal melhorar o desempenho de chatterbots em diálogos livres com usuários. Chatterbots são sistemas computacionais que se propõem a conversar em linguagem natural como se fossem humanos. O primeiro desses sistemas foi ELIZA, desenvolvido em 1965 por Weizenbaum. Desde então, inúmeros sistemas foram produzidos com esse mesmo objetivo. Porém, uma série de problemas ainda continuam em aberto, dentre os quais, o tratamento de intenção, questão central na interpretação de diálogos naturais. Nesse sentido, desenvolvemos um mecanismo para tratamento de intenção para ser incorporado a chatterbots baseados em AIML. Adotamos como base conceitual para o trabalho a Teoria da Análise da Conversação (TAC), por considerar a intenção em pares adjacentes, e não apenas na sentença do falante, como a Teoria dos Atos de Fala. Com base na TAC e em experimentos realizados, selecionamos um conjunto de intenções, que foram utilizadas na criação de regras em AIML que utilizam informações de intencionalidade para interpretar e gerar sentenças em diálogos naturais. A solução final foi testada em uma série de experimentos, e demonstrou ser capaz de corrigir alguns problemas presentes em diálogos com chatterbots. Por exemplo, o sistema baseado em AIML padrão tratou 40% das sentenças dos usuários como sendo desconhecidas, enquanto o nosso sistema classificou apenas 3,5% das sentenças como totalmente desconhecidas. Além disso, o sistema foi capaz de manter a estrutura global dos diálogos, criticando turnos de abertura ou fechamento que foram ditos no desenvolvimento, ou turnos de desenvolvimento ditos na abertura ou fechamento. Por fim, implementamos três aplicações com chatterbots, o que demonstra que a solução adotada favorece o reuso de categorias em bases AIML, processo extremamente custoso do ponto de vista de engenharia de software com os sistemas atuais

With the rising popularity of chatbots, not just in entertainment but in e-commerce and online chat support, it’s become increasingly important to be able to quickly set up chatbots that can respond to simple questions. This study examines which of two algorithms for automatic generation of chatbot knowledge bases, First Word Search or Most Significant Word Search, is able to generate the responses that are the most relevant to the topic of a question. It also examines how text corpora might be used as a source from which to generate chatbot knowledge bases. Two chatbots were developed for this project, one for each of the two algorithms that are to be examined. The chatbots are evaluated through a survey where the participants are asked to choose which of the algorithms they thought chose the response that was most relevant to a question. Based on the survey we conclude that Most Significant Word Search is the algorithm that picks the most relevant responses. Most Significant Word Search has a significantly higher chance of generating a response that is relevant to the topic. However, how well a text corpus works as a source for knowledge bases depends entirely on the quality and nature of the corpus. A corpus consisting of written dialogue is likely more suitable for conversion into a knowledge base.

Chatbots are software agents that interact with the user in a conversation. The main goal of their creation was to resemble a human being in the way they perform said interaction, trying to make the user think he/she is writing to another human being. This has been implemented with varying degrees of success. One of the most popular languages for the definition of a chatbot knowledge base is AIML.This thesis focuses on the implementation of an AIML interpreter written in Javascript to allow for a web-based client-side specific usage of AIML chatbots. The interpreter must guarantee the compliance of properly formed AIML documents, perform all the necessary pre-processing duties for the correct usage of the chatbot and ensure the correctness of both pattern matching of user input and chatbot response.The interpreter fully exploits the DOM tree manipulation functions of the jQuery library to achieve said goals, treating AIML files as if they were normal XML files. The result is a well performing, fully functional AIML interpreter tailored around AIML 1.0 specification.

Made available in DSpace on 2015-04-11T14:02:39Z (GMT). No. of bitstreams: 1 Marcio Alencar.pdf: 1656491 bytes, checksum: a441863efe54446babff31c15171027b (MD5) Previous issue date: 2011-12-19 / With the widespread use of Virtual Learning Environments (VLE) in various educational institutions, usually in education courses distance, the task of monitoring the activities of students per guardians and mediators to achieve levels of quality have been a increasing work. To follow up the students in these new technologies require new thinking and attitudes of educators in these environments and new solutions by the designers of this class of systems. This paper describes architectures based on Multiagent Systems, focused on the concept of perception, designed to assist students and tutors on completion and monitoring of activities in distance education courses. The systems implemented according to the proposed architectures, help tutors and students through a discussion forum, solving doubts about the course and recommend the realization of activities that the student has not completed, favoring facilitating the smooth running of the course and collaboration among the other participants. Each proposed architecture there was a prototype implemented and evaluated, resulting in proposals for improvements in the next version. The results obtained during the experiments demonstrate the importance of using Multi-agent Systems in Virtual Learning Environments, supporting the realization of activities of the course participants and monitored by the tutors. / Com a disseminação do uso de Ambientes Virtuais de Aprendizagem (AVA) por diversas instituições de ensino, notadamente em cursos de Educação a Distância, a tarefa de acompanhamento das atividades dos alunos por tutores e mediadores para atingir níveis de qualidade têm sido um trabalho cada vez maior. Realizar o acompanhamento dos alunos nessas novas tecnologias, requerer novas reflexões e posturas de educadores nestes ambientes e novas soluções por parte dos projetistas desta classe de sistemas. Esta dissertação descreve arquiteturas baseadas em Sistemas Multiagente, focadas no conceito de percepção, criadas para auxiliar alunos e tutores na conclusão e acompanhamento de atividades em cursos de Educação a Distância. Os sistemas implementados seguindo as arquiteturas propostas auxiliam alunos e tutores por meio de um fórum de discussão, sanando dúvidas sobre o curso, além de recomendar a realização de atividades que o aluno não tenha concluído, favorecendo o bom andamento do curso e a colaboração entre os demais participantes. Cada arquitetura proposta teve um protótipo implementado e avaliado, resultando em propostas de melhorias na versão seguinte. Os resultados obtidos durante as experimentações demostram a importância do uso de Sistemas Multiagente em Ambientes Virtuais de Aprendizagem, apoiando a execução de atividades dos cursistas e o acompanhamento por parte dos tutores.

Digitalizing education and reinventing the learning experience is one of the big challenges in this age of information. In the eld of E-learning, the application of a chatbot as part of the education has shown interesting potential, both as a teaching and administrative tool. Chatbots have been 'trending' for a few years and quite a few papers examining it in the educational sector has been published, albeit very little interest seems to have been given to the summation of this knowledge. In an attempt to fill the knowledge gap this thesis performed a literature study to examine the documented features and possible uses for chatbots in an educational context. Since quite a few chatbot technologies have been developed at this time and exhibit varied functions, this study was limited to only examine bots based on the XML derived language AIML. The results imply that chatbots in education have quite a few uses and even more possible features. An AIML-based chatbot can be both simple and complex to implement, all depending on the effort put into implementation. The tool is diverse and may be used for many different purposes and aims, the only limitation being the creators' creativity and imagination.

Natural language understanding has been a persistent challenge to researchers in various computer science fields, in a number of applications ranging from user support systems to entertainment and online teaching. A long term goal of the Artificial Intelligence field is to implement mechanisms that enable computers to emulate human dialogue. The recently developed ALICEbots, virtual agents with underlying AIML scripts, by A.L.I.C.E. foundation, use AIML scripts - a subset of XML - as the underlying pattern database for question answering. Their goal is to enable pattern-based, stimulus-response knowledge content to be served, received and processed over the Web, or offline, in the manner similar to HTML and XML. In this thesis, we describe a system that converts the AIML scripts to Prolog clauses and reuses them as part of a knowledge processor. The inference mechanism developed in this thesis is able to successfully match the input pattern with our clauses database even if words are missing. We also emulate the pattern deduction algorithm of the original logic deduction mechanism. Our rules, compatible with Semantic Web standards, bring structure to the meaningful content of Web pages and support interactive content retrieval using natural language.