BROWSE
Detail
Conference Paper
Extracting Template for Knowledge-based Question-answering using Conditional Random Fields
Cited - time in 
Share 
Share
- Authors
- Changki Lee, Ji-Hyun Wang, Hyeon-Jin Kim, Myung-Gil Jang
- Issue Date
- 2005-08
- Citation
- International Conference on Research and Development in Information Retrieval 2005, pp.1-8
- Language
- English
- Type
- Conference Paper
- Abstract
- In this paper, we present an information extraction system that extracts template elements for a question-answering (QA) system in the domain of encyclopedia. We use Conditional Random Fields to extract templates from the texts of an encyclopedia. Using the proposed approach, we could achieve a 74.89% precision and a 55.77% F1 in the template extraction. In the question classification, we could archive an 83.6% precision and a 65.4% recall. Finally, in the Knowledge-based QA (including template extraction procedure), we could archive an 81.3% precision and a 33.3% recall. The result demonstrated that our approach is feasible and effective for template extraction for QA.
- KSP Keywords
- Conditional Random Field(CRF), Extraction system, Knowledge-based question-answering, information extraction, question classification, template extraction