Constructing literature abstracts by computer: techniques and prospects
Information Processing and Management: an International Journal - Special issue on natural language processing and information retrieval
A translation approach to portable ontology specifications
Knowledge Acquisition - Special issue: Current issues in knowledge modeling
Computers in Industry - Special double issue: WET ICE '95
Web document clustering: a feasibility demonstration
Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval
Creating Semantic Web Contents with Protégé-2000
IEEE Intelligent Systems
Ontology as a Requirements Engineering Product
RE '03 Proceedings of the 11th IEEE International Conference on Requirements Engineering
Proceedings of the 2nd international conference on Knowledge capture
Text analysis and knowledge mining system
IBM Systems Journal
Japanese dependency structure analysis based on support vector machines
EMNLP '00 Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 13
Japanese dependency analysis using cascaded chunking
COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Extracting product features and opinions from reviews
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Mining opinion features in customer reviews
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Term extraction from sparse, ungrammatical domain-specific documents
Expert Systems with Applications: An International Journal
Hi-index | 12.05 |
In this paper, a method to extract knowledge from a set of surveyors' reports is proposed. Many surveyors from shipping companies are working in shipyards to improve the quality and to meet requirements of the ship owner. At present, the reports from surveyors are used only for managing the status of problems of the product. The proposed method here has three steps. First, the description field of the reports which contains information about some trouble is summarized in a pair of a component name and a trouble name in the failure database; this is made possible through text-processing technology. Second, synonymous component and trouble names are consolidated into normalized terms using synonym ontology to prepare this information for statistical analysis. The synonym ontology is developed prior to this procedure. The system evaluates frequent trouble records by classifying the records using component and process ontology. In the last step, the designers extract knowledge from the information generated by the system. The results illustrate common design problems, and the method is proved to be useful.