Abstract
Key-phrase extraction plays useful a role in the research area of Information Systems (IS) such as digital libraries. Short metadata like key phrases could be beneficial for searchers to understand the concepts of documents' concept. This paper evaluates the effectiveness of different supervised learning techniques on biomedical full-text: Naïve Bayes, linear regression, SVMs (reg1/2), all of which could be embedded inside an IS for document search. We use these techniques to extract key phrases from PubMed. We evaluate the performance of these systems using the well-established holdout validation method. The contributions of the paper are comparison among different classifier techniques, and a comparison of performance differences between full-text and abstract. We conducted experiments and found that SVMreg-1 improves the performance of key-phrase extraction from full-text while Naïve Bayes improves from the abstracts. These techniques should be considered for use in information system search functionality. Additional research issues also are identified.
| Original language | English |
|---|---|
| Title of host publication | 15th Americas Conference on Information Systems 2009, AMCIS 2009 |
| Pages | 2992-3000 |
| Number of pages | 9 |
| Publication status | Published - 2009 Dec 1 |
| Event | 15th Americas Conference on Information Systems 2009, AMCIS 2009 - San Francisco, CA, United States Duration: 2009 Aug 6 → 2009 Aug 9 |
Publication series
| Name | 15th Americas Conference on Information Systems 2009, AMCIS 2009 |
|---|---|
| Volume | 5 |
Other
| Other | 15th Americas Conference on Information Systems 2009, AMCIS 2009 |
|---|---|
| Country | United States |
| City | San Francisco, CA |
| Period | 09/8/6 → 09/8/9 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Computer Networks and Communications
- Information Systems
- Library and Information Sciences
Cite this
}
Extraction of key-phrases from biomedical full-text with supervised learning techniques. / Qi, Yanliang; Yagci, Artun I.; Song, Min.
15th Americas Conference on Information Systems 2009, AMCIS 2009. 2009. p. 2992-3000 (15th Americas Conference on Information Systems 2009, AMCIS 2009; Vol. 5).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Extraction of key-phrases from biomedical full-text with supervised learning techniques
AU - Qi, Yanliang
AU - Yagci, Artun I.
AU - Song, Min
PY - 2009/12/1
Y1 - 2009/12/1
N2 - Key-phrase extraction plays useful a role in the research area of Information Systems (IS) such as digital libraries. Short metadata like key phrases could be beneficial for searchers to understand the concepts of documents' concept. This paper evaluates the effectiveness of different supervised learning techniques on biomedical full-text: Naïve Bayes, linear regression, SVMs (reg1/2), all of which could be embedded inside an IS for document search. We use these techniques to extract key phrases from PubMed. We evaluate the performance of these systems using the well-established holdout validation method. The contributions of the paper are comparison among different classifier techniques, and a comparison of performance differences between full-text and abstract. We conducted experiments and found that SVMreg-1 improves the performance of key-phrase extraction from full-text while Naïve Bayes improves from the abstracts. These techniques should be considered for use in information system search functionality. Additional research issues also are identified.
AB - Key-phrase extraction plays useful a role in the research area of Information Systems (IS) such as digital libraries. Short metadata like key phrases could be beneficial for searchers to understand the concepts of documents' concept. This paper evaluates the effectiveness of different supervised learning techniques on biomedical full-text: Naïve Bayes, linear regression, SVMs (reg1/2), all of which could be embedded inside an IS for document search. We use these techniques to extract key phrases from PubMed. We evaluate the performance of these systems using the well-established holdout validation method. The contributions of the paper are comparison among different classifier techniques, and a comparison of performance differences between full-text and abstract. We conducted experiments and found that SVMreg-1 improves the performance of key-phrase extraction from full-text while Naïve Bayes improves from the abstracts. These techniques should be considered for use in information system search functionality. Additional research issues also are identified.
UR - http://www.scopus.com/inward/record.url?scp=79954623508&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79954623508&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:79954623508
SN - 9781615675814
T3 - 15th Americas Conference on Information Systems 2009, AMCIS 2009
SP - 2992
EP - 3000
BT - 15th Americas Conference on Information Systems 2009, AMCIS 2009
ER -