Description Logic based Knowledge Representation for Information Extraction and Query Processing

Abstract

Keyword-based search engines provide poor recall due to the fact that they ignore specialization/generalization and synonym handling. They also exhibit low precision that is retrieval with large amount of irrelevant information. This is due to the fact that the knowledge representation of the document is not well established. This work attempts to capture effectively the knowledge of the document using knowledge representation formalism Description Logic (DL) and represents the concepts as a DL hierarchy. The greatest advantage of representing knowledge in DL is that the system is now able to handle inconsistency and Incompleteness present in the user queries. This is useful to the naive user who is unfamiliar in framing structured queries. Finally the performance of the proposed system is evaluated with that of content word based retrieval based on the performance metrics precision and recall.

Indexing terms:

• Information retrieval
• Information extraction
• Text mining
• description logic

Additional information

Notes on contributors

D Manjula

D Manjula completed her BE in Electronics and Communication from Thigarajar College of Engineering, Madurai in 1983, ME in Computer Science from Anna University, Chennai in 1987 and PhD from College of Engineering, Anna University, Chennai. She is working as a Selection grade Lecturer in the Department of computer Science and Engineering, Anna University. Her areas of interest include Text Mining, Information Retrieval, Parallel Processing, Parallel and Distributed Databases and Artificial Intelligence.

T V Geetha

T V Geetha completed her BE in Electronics and Communication Engineering in 1982, ME in Computer Science and Engineering in 1986 and PhD from College of Engineering, Anna University, Chennai. Currently she is working as a Director and Professor in the Department of Engineering, Anna University. Her areas of interest include Natural Language Processing, Text Mining, Information Retrieval, Tamil Computing, Indian Language Logistics, Artificial Intelligence and Intelligent Data Bases.