Abstract
We propose a statistical frame-based approach (FBA) for natural language processing, and demonstrate its advantage over traditional machine learning methods by using topic detection as a case study. FBA perceives and identifies semantic knowledge in a more general manner by collecting important linguistic patterns within documents through a unique flexible matching scheme that allows word insertion, deletion and substitution (IDS) to capture linguistic structures within the text. In addition, FBA can also overcome major issues of the rule-based approach by reducing human effort through its highly automated pattern generation and summarization. Using Yahoo! Chinese news corpus containing about 140,000 news articles, we provide a comprehensive performance evaluation that demonstrates the effectiveness of FBA in detecting the topic of a document by exploiting the semantic association and the context within the text. Moreover, it outperforms common topic models like Näive Bayes, Vector Space Model, and LDA-SVM.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014 |
| Publisher | Faculty of Pharmaceutical Sciences, Chulalongkorn University |
| Pages | 75-84 |
| Number of pages | 10 |
| ISBN (Electronic) | 9786165518871 |
| Publication status | Published - 2014 |
| Externally published | Yes |
| Event | 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014 - Phuket, Thailand Duration: Dec 12 2014 → Dec 14 2014 |
Conference
| Conference | 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014 |
|---|---|
| Country | Thailand |
| City | Phuket |
| Period | 12/12/14 → 12/14/14 |
Fingerprint
ASJC Scopus subject areas
- Language and Linguistics
- Computer Science (miscellaneous)
Cite this
Semantic frame-based statistical approach for topic detection. / Chang, Yung Chun; Hsieh, Yu Lun; Chen, Cen Chieh; Liu, Chad; Lu, Chun Hung; Hsu, Wen Lian.
Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014. Faculty of Pharmaceutical Sciences, Chulalongkorn University, 2014. p. 75-84.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Semantic frame-based statistical approach for topic detection
AU - Chang, Yung Chun
AU - Hsieh, Yu Lun
AU - Chen, Cen Chieh
AU - Liu, Chad
AU - Lu, Chun Hung
AU - Hsu, Wen Lian
PY - 2014
Y1 - 2014
N2 - We propose a statistical frame-based approach (FBA) for natural language processing, and demonstrate its advantage over traditional machine learning methods by using topic detection as a case study. FBA perceives and identifies semantic knowledge in a more general manner by collecting important linguistic patterns within documents through a unique flexible matching scheme that allows word insertion, deletion and substitution (IDS) to capture linguistic structures within the text. In addition, FBA can also overcome major issues of the rule-based approach by reducing human effort through its highly automated pattern generation and summarization. Using Yahoo! Chinese news corpus containing about 140,000 news articles, we provide a comprehensive performance evaluation that demonstrates the effectiveness of FBA in detecting the topic of a document by exploiting the semantic association and the context within the text. Moreover, it outperforms common topic models like Näive Bayes, Vector Space Model, and LDA-SVM.
AB - We propose a statistical frame-based approach (FBA) for natural language processing, and demonstrate its advantage over traditional machine learning methods by using topic detection as a case study. FBA perceives and identifies semantic knowledge in a more general manner by collecting important linguistic patterns within documents through a unique flexible matching scheme that allows word insertion, deletion and substitution (IDS) to capture linguistic structures within the text. In addition, FBA can also overcome major issues of the rule-based approach by reducing human effort through its highly automated pattern generation and summarization. Using Yahoo! Chinese news corpus containing about 140,000 news articles, we provide a comprehensive performance evaluation that demonstrates the effectiveness of FBA in detecting the topic of a document by exploiting the semantic association and the context within the text. Moreover, it outperforms common topic models like Näive Bayes, Vector Space Model, and LDA-SVM.
UR - http://www.scopus.com/inward/record.url?scp=84994070599&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84994070599&partnerID=8YFLogxK
M3 - Conference contribution
SP - 75
EP - 84
BT - Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014
PB - Faculty of Pharmaceutical Sciences, Chulalongkorn University
ER -