Name: Marta Talitha Carvalho Freire Mendes
Type: MSc dissertation
Publication date: 31/08/2012
Advisor:

Namesort descending Role
Davidson Cury Advisor *

Examining board:

Namesort descending Role
Alexandre Ibrahim Direne External Examiner *
Credine Silva de Menezes Co advisor *
Davidson Cury Advisor *
Orivaldo de Lira Tavares Internal Examiner *

Summary: When people want to learn a concept, the most common way is to use a search engine like: Google, Yahoo, Bing, among others. A natural language query is submitted to a search tool and which returns a lot of pages related to the concept studied. Usually the returned pages are listed and organized mainly based on the combination of keywords instead of using the interpretation and relevance of the terms found. The user must have read a lot of pages and selects the most appropriate to his needs. This kind of behavior takes time and focus on user-learner is dispersed to his goal.
The use of intelligent systems that support the clarification of doubt has intent to solve this problem, presenting the most accurate answers to questions or sentences in natural language. Examples clarification of doubt systems are: question-answer system, helpdesk intelligent among others.
This work uses an architectural approach to a question answering system based on three steps: question analysis, selection and extraction of the answer and answer generation. One of the merits of this architecture is to use techniques that complement each other, such as ontologies, information retrieval techniques and a knowledge base written in AIML language to extract the answer quickly. The focus of this work is to answer questions WH-question (What, Who, When, Where, What, Who) of the English language.

Access to document

Acesso à informação
Transparência Pública

© 2013 Universidade Federal do Espírito Santo. Todos os direitos reservados.
Av. Fernando Ferrari, 514 - Goiabeiras, Vitória - ES | CEP 29075-910