Towards an enhanced framework for learning semantic relation classification
Most of the research in this area depends on NLP techniques, machine learning, and statistical approaches, but the challenging issue here is to provide a general learning framework in an automated way that make use of different kinds of contextual knowledge, and to make use of that framework to enri...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2011
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/552/ http://ir.unimas.my/id/eprint/552/1/towards%20an%20enhanced%20framework%20for%20learning%20semantic.pdf |
| Summary: | Most of the research in this area depends on NLP techniques, machine learning, and statistical approaches, but the challenging issue here is to provide a general learning framework in an automated way that make use of different kinds of contextual knowledge, and to make use of that framework to enrich the ontology with new relations, hence facilitate ontology acquisition. We have developed a unique framework for acquiring ontology relations from a large collection of domain independent texts. Our experiments on the proposed approach have shown promising results, even at an early state. The main contribution of this work lies in the semantic validation of causation relationships based on thorough corpus linguistics. |
|---|