| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 5.43 MB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
Perante o constante crescimento do volume de informação disponível na internet, os motores de pesquisa desempenham um papel fundamental na forma como facilmente podemos encontrar a informação que procuramos. A utilização da Inteligência Artificial no processamento de língua natural aplicada aos motores de pesquisa de conteúdos, tem permitido que estes correspondam de forma mais inteligente, não só na vertente mais habitual para encontrar os documentos mais relevantes, mas também no entendimento das intenções do utilizador, apresentando respostas diretas às questões colocadas. Nos sistemas de eLearning, o crescimento da informação não foge à regra, acompanhando a tendência de transição digital, quer pela criação de novos conteúdos nos mais variados formatos, quer pela transformação digital dos manuais escolares. Este projeto, EVGuru, pretende explorar as técnicas mais adequadas de Inteligência Artificial aplicada ao processamento de língua natural, que permitam a criação de uma experiência de pesquisa inteligente de conteúdos educativos. O projeto é desenvolvido considerando uma eventual integração na plataforma de eLearning Escola Virtual da Porto Editora. Para tal, esta investigação é acompanhada do desenho da arquitetura dos componentes necessários à implementação de um protótipo, capaz de encontrar uma resposta direta para a questão colocada pelo utilizador, através da pesquisa nos textos de um manual escolar. Durante a realização do projeto, vários modelos foram testados em diferentes tarefas do processamento de língua natural, como classificação de textos, questões e respostas e geração de questões.
Due to the constantly growing of the information available on the internet, search engines play a key role in how easily we can find the information we are searching for. The use of Artificial Intelligence in natural language processing applied to content search engines, has allowed them to match more intelligently, not only in the most usual way to find the most relevant documents, but also in understanding the user's intentions, providing direct answers to the questions asked. In eLearning platforms, the growth of information is not exception, following the trend of digital transition, either through the creation of new content in the most varied formats, or through the digital transformation of school textbooks. This project, EVGuru, aims to explore the most appropriate techniques of Artificial Intelligence applied to natural language processing, which allow the creation of an intelligent search experience for educational content. The project is developed considering an eventual integration into the Porto Editora Escola Virtual eLearning platform. Therefore, this investigation is accompanied by the components architecture design that will be necessary for the implementation of a prototype, capable of finding a direct answer to the question posed by the user, through the search in the texts of a school textbook. During the project, several models were tested in different tasks of natural language processing, such as text classification, questions and answers and question generation.
Due to the constantly growing of the information available on the internet, search engines play a key role in how easily we can find the information we are searching for. The use of Artificial Intelligence in natural language processing applied to content search engines, has allowed them to match more intelligently, not only in the most usual way to find the most relevant documents, but also in understanding the user's intentions, providing direct answers to the questions asked. In eLearning platforms, the growth of information is not exception, following the trend of digital transition, either through the creation of new content in the most varied formats, or through the digital transformation of school textbooks. This project, EVGuru, aims to explore the most appropriate techniques of Artificial Intelligence applied to natural language processing, which allow the creation of an intelligent search experience for educational content. The project is developed considering an eventual integration into the Porto Editora Escola Virtual eLearning platform. Therefore, this investigation is accompanied by the components architecture design that will be necessary for the implementation of a prototype, capable of finding a direct answer to the question posed by the user, through the search in the texts of a school textbook. During the project, several models were tested in different tasks of natural language processing, such as text classification, questions and answers and question generation.
Description
Keywords
eLearning Motor de pesquisa Machine learning Inteligência artificial Questões e respostas Reading comprehension Search engines Artificial intelligence Question answering