Titulo Estágio
Semantic Search in an Information Repository
Área Tecnológica
Inteligência Artificial
Local do Estágio
LIA2 - DEI
Enquadramento
Google is synonym of search, but search in Google is limited. It looks for symbols not the meaning of the words that the user put in the query. Besides this limitation, search engines like Google do not provide answers to most of your searches, especially the most complex ones. They provide the user a list of documents, where the answer might be. Another problem with Google-like search is the overwhelming of information that it provides. Nevertheless, most of us use Google (I do :-) and it is a great tool for Web search.
What we want to explore in this thesis proposal, is the use of Semantic Web and Natural Language Processing mechanisms in search – Semantic Search. This work proposal includes the creation of a search engine that is able to extract semantic information for documents, understand the meaning of the user query and give the user an answer to the user query, not a set of documents. The work is intended to be applied to a closed information repository of documents, like the Wikipedia. The addressed language is the English as the first target, but the Portuguese is not discarded.
Objetivo
The objective of this thesis is the creation of a prototype using a specific information repository. The candidate should explore the indexing of documents (how to extract information from documents and represent it using Semantic Web technologies), understand the user query, retrieve relevant information, organize it and show it to the user in a friendly format. The approach developed should be tested in terms of performance.
The candidate will elaborate a state of the art study on the topics and technologies covered by this thesis.
After this initial phase, the candidate will implement a prototype using the most appropriate approaches. The work concludes with the prototype experimentation and thesis writing.
Plano de Trabalhos - Semestre 1
- State of the Art [Set – Nov]
- Information Retrieval
- Semantic Web Technologies
- Related Work
- Analysis and Specification [Dec]
- Definition of System Requirements
- Use Case Definition
- Design and Specification
- Thesis Proposal Writing [Dec – Feb]
Plano de Trabalhos - Semestre 2
- Prototype Development [Mar – Jun]
- Prototype Experimentation [Jun – Jul]
- Funtional Tests
- Search Quality Tests
- Performance Tests
- Thesis Writing [Jun – Jul]
Condições
PC for working is provided if needed, as well as server for development and experimentation. A place of work in the LIA2 lab is also available. The attribution of a scholarship is possible, but at this moment not guarantied.
Observações
The research work will take place in the Knowledge and Intelligent Systems laboratory of the Cognitive and Multimedia Systems group of CISUC.
Orientador
Paulo Gomes
pgomes@dei.uc.pt 📩