IEICE TRANSACTIONS on Information
Sentence Topics Based Knowledge Acquisition for Question Answering
Summary :
This paper presents a knowledge acquisition method using sentence topics for question answering. We define templates for information extraction by the Korean concept network semi-automatically. Moreover, we propose the two-phase information extraction model by the hybrid machine learning such as maximum entropy and conditional random fields. In our experiments, we examined the role of sentence topics in the template-filling task for information extraction. Our experimental result shows the improvement of 18% in F-score and 434% in training speed over the plain CRF-based method for the extraction task. In addition, our result shows the improvement of 8% in F-score for the subsequent QA task.
- Publication
- IEICE TRANSACTIONS on Information Vol.E91-D No.4 pp.969-975
- Publication Date
- 2008/04/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e91-d.4.969
- Type of Manuscript
- Special Section PAPER (Special Section on Knowledge-Based Software Engineering)
- Category
- Knowledge Engineering
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hyo-Jung OH, Bo-Hyun YUN, "Sentence Topics Based Knowledge Acquisition for Question Answering" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 4, pp. 969-975, April 2008, doi: 10.1093/ietisy/e91-d.4.969.
Abstract: This paper presents a knowledge acquisition method using sentence topics for question answering. We define templates for information extraction by the Korean concept network semi-automatically. Moreover, we propose the two-phase information extraction model by the hybrid machine learning such as maximum entropy and conditional random fields. In our experiments, we examined the role of sentence topics in the template-filling task for information extraction. Our experimental result shows the improvement of 18% in F-score and 434% in training speed over the plain CRF-based method for the extraction task. In addition, our result shows the improvement of 8% in F-score for the subsequent QA task.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.4.969/_p
Copy
@ARTICLE{e91-d_4_969,
author={Hyo-Jung OH, Bo-Hyun YUN, },
journal={IEICE TRANSACTIONS on Information},
title={Sentence Topics Based Knowledge Acquisition for Question Answering},
year={2008},
volume={E91-D},
number={4},
pages={969-975},
abstract={This paper presents a knowledge acquisition method using sentence topics for question answering. We define templates for information extraction by the Korean concept network semi-automatically. Moreover, we propose the two-phase information extraction model by the hybrid machine learning such as maximum entropy and conditional random fields. In our experiments, we examined the role of sentence topics in the template-filling task for information extraction. Our experimental result shows the improvement of 18% in F-score and 434% in training speed over the plain CRF-based method for the extraction task. In addition, our result shows the improvement of 8% in F-score for the subsequent QA task.},
keywords={},
doi={10.1093/ietisy/e91-d.4.969},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Sentence Topics Based Knowledge Acquisition for Question Answering
T2 - IEICE TRANSACTIONS on Information
SP - 969
EP - 975
AU - Hyo-Jung OH
AU - Bo-Hyun YUN
PY - 2008
DO - 10.1093/ietisy/e91-d.4.969
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2008
AB - This paper presents a knowledge acquisition method using sentence topics for question answering. We define templates for information extraction by the Korean concept network semi-automatically. Moreover, we propose the two-phase information extraction model by the hybrid machine learning such as maximum entropy and conditional random fields. In our experiments, we examined the role of sentence topics in the template-filling task for information extraction. Our experimental result shows the improvement of 18% in F-score and 434% in training speed over the plain CRF-based method for the extraction task. In addition, our result shows the improvement of 8% in F-score for the subsequent QA task.
ER -
English
