الفهرس | Only 14 pages are availabe for public view |
Abstract In this thesis, we showed a technique that can successfully retrieve the relevant biological documents and tackles the extracting of semantic relationships from biological documents. The system also constructs a term - relation table that accelerates the relation extracting part. The proposed method offers another usage of the system so the researchers can use it to figure out the relationship between two biological terms through the available information in the biological documents. The measures the values of accuracy of system documents retrieved. The method improves semantic performance of the system since it retrieves the relationship between the input words. Term- relation table improves the extracting part since it becomes a reference to all the relationships exist between the biological terms found in the corpus. The proposed method helps the researchers to get more information about the input words by extracting the all relationships between these terms from the biological documents. Future Work The proposed system is domain-specific which can be generalized to be applied in many different domains. The proposed system should be speed up using indexing and hashing of the corpus documents to fast reterival process of documents. The proposed system is evalauted using different metrics which are limited for information reterival and didn’t include aspects of parllization and distributed enviornments. The proposed system is intended to be available in cloud computing as a service on demand. |