Inproceedings,
Information extraction from unstructured data using RDF
2016 International Conference on ICT in Business Industry Government (ICTBIG), page 1-6. (November 2016)
DOI: 10.1109/ICTBIG.2016.7892635
Abstract
The Internet exhibits a gigantic measure of helpful data which is generally designed for its users, which makes it hard to extract applicable information from different sources. Accordingly, the accessibility of strong, adaptable Information Extraction framework that consequently concentrate structured data such as, entities, relationships between entities, and attributes from unstructured or semi-structured sources. But somewhere during extraction of information may lead to the loss of its meaning, which is absolutely not feasible. Semantic Web adds solution to this problem. It is about providing meaning to the data and allow the machine to understand and recognize these augmented data more accurately. The proposed system is about extracting information from research data of IT domain like journals of IEEE, Springer, etc., which aid researchers and the organizations to get the data of journals in an optimized manner so the time and hard work of surfing and reading the entire journal's papers or articles reduces. Also the accuracy of the system is taken care of using RDF, the data extracted has a specific declarative semantics so that the meaning of the research papers or articles during extraction remains unchanged. In addition, the same approach shall be applied on multiple documents, so that time factor can get saved.
