Abstract
Detecting the topic of documents can help readers construct the background of the topic and facilitate document comprehension. In this paper, we propose a semantic frame-based topic detection (SFTD) that simulates such process in human perception. We take advantage of multiple knowledge sources and extracted discriminative patterns from documents through a highly automated, knowledge-supported frame generation and matching mechanisms. Using a Chinese news corpus containing over 111,000 news articles, we provide a comprehensive performance evaluation which demonstrates that our novel approach can effectively detect the topic of a document by exploiting the syntactic structures, semantic association, and the context within the text. Experimental results show that SFTD is comparable to other well-known topic detection methods.
| Original language | English |
|---|---|
| Pages (from-to) | 391-401 |
| Number of pages | 11 |
| Journal | Soft Computing |
| Volume | 21 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - Jan 1 2017 |
| Externally published | Yes |
Fingerprint
Keywords
- Partial matching
- Semantic class
- Semantic frame
- Topic detection
ASJC Scopus subject areas
- Theoretical Computer Science
- Software
- Geometry and Topology
Cite this
A semantic frame-based intelligent agent for topic detection. / Chang, Yung Chun; Hsieh, Yu Lun; Chen, Cen Chieh; Hsu, Wen Lian.
In: Soft Computing, Vol. 21, No. 2, 01.01.2017, p. 391-401.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A semantic frame-based intelligent agent for topic detection
AU - Chang, Yung Chun
AU - Hsieh, Yu Lun
AU - Chen, Cen Chieh
AU - Hsu, Wen Lian
PY - 2017/1/1
Y1 - 2017/1/1
N2 - Detecting the topic of documents can help readers construct the background of the topic and facilitate document comprehension. In this paper, we propose a semantic frame-based topic detection (SFTD) that simulates such process in human perception. We take advantage of multiple knowledge sources and extracted discriminative patterns from documents through a highly automated, knowledge-supported frame generation and matching mechanisms. Using a Chinese news corpus containing over 111,000 news articles, we provide a comprehensive performance evaluation which demonstrates that our novel approach can effectively detect the topic of a document by exploiting the syntactic structures, semantic association, and the context within the text. Experimental results show that SFTD is comparable to other well-known topic detection methods.
AB - Detecting the topic of documents can help readers construct the background of the topic and facilitate document comprehension. In this paper, we propose a semantic frame-based topic detection (SFTD) that simulates such process in human perception. We take advantage of multiple knowledge sources and extracted discriminative patterns from documents through a highly automated, knowledge-supported frame generation and matching mechanisms. Using a Chinese news corpus containing over 111,000 news articles, we provide a comprehensive performance evaluation which demonstrates that our novel approach can effectively detect the topic of a document by exploiting the syntactic structures, semantic association, and the context within the text. Experimental results show that SFTD is comparable to other well-known topic detection methods.
KW - Partial matching
KW - Semantic class
KW - Semantic frame
KW - Topic detection
UR - http://www.scopus.com/inward/record.url?scp=84928743034&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84928743034&partnerID=8YFLogxK
U2 - 10.1007/s00500-015-1695-4
DO - 10.1007/s00500-015-1695-4
M3 - Article
VL - 21
SP - 391
EP - 401
JO - Soft Computing
JF - Soft Computing
SN - 1432-7643
IS - 2
ER -