TY - JOUR
T1 - CMedPort
T2 - An integrated approach to facilitating Chinese medical information seeking
AU - Zhou, Yilu
AU - Qin, Jialun
AU - Chen, Hsinchun
N1 - Funding Information:
This project was supported in part by an NSF Digital Library Initiative-2 grant, PI: H. Chen, “High-performance Digital Library Systems: From Information Retrieval to Knowledge Management,” IIS-9817473, April 1999-March 2002. We would like to thank the following people for their help and comments: Zan Huang, Yiwen Zhang, Wingyan Chung, Gang Wang, Michael Chau, Daniel McDonald, Byron Marshall, Alan Yip, Mark Chen, Gondy Leroy, Thian-Huat Ong, Wai-Ki Sung, Chienting Lin, and Lu Tseng. We would also like to thank the AI Lab team members who developed the AI Lab SpidersRUs toolkit, the Mutual Information software, and the Web Weaver package. Finally, we also want to thank the domain experts and all our subjects who took part in the evaluation study.
PY - 2006/12
Y1 - 2006/12
N2 - As the number of non-English resources available on the Web is increasing rapidly, developing information retrieval techniques for non-English languages is becoming an urgent and challenging issue. In this research to facilitate information seeking in a multilingual world, we focused on discovering how search-engine techniques developed for English could be generalized for use with other languages. We proposed a general framework incorporating a focused collection-building technique, a generic language processing ability, an integration of information resources, and a post-retrieval analysis module. Based on this approach, we developed CMedPort, a Chinese Web portal in the medical domain that not only allows users to search for Web pages from local collections and meta-search engines but also provides encoding conversion between simplified and traditional Chinese to support cross-regional search and document summarization and categorization. User studies were conducted to compare the effectiveness and efficiency of CMedPort with those of three major Chinese search engines. Results indicate that CMedPort achieved similar accuracy for search tasks, but exhibited significantly higher recall than each of the three search engines as well as higher precision than two of the search engines for browse tasks. There were no significant differences among the efficiency measures for CMedPort and benchmarks systems. A post-questionnaire regarding system usability indicated that CMedPort achieved significantly higher user satisfaction than any of the three benchmark systems. The subjects especially liked CMedPort's categorizer, commenting that it helped improve understanding of search results. These encouraging outcomes suggest a promising future for applying our approach to Internet searching and browsing in a multilingual world.
AB - As the number of non-English resources available on the Web is increasing rapidly, developing information retrieval techniques for non-English languages is becoming an urgent and challenging issue. In this research to facilitate information seeking in a multilingual world, we focused on discovering how search-engine techniques developed for English could be generalized for use with other languages. We proposed a general framework incorporating a focused collection-building technique, a generic language processing ability, an integration of information resources, and a post-retrieval analysis module. Based on this approach, we developed CMedPort, a Chinese Web portal in the medical domain that not only allows users to search for Web pages from local collections and meta-search engines but also provides encoding conversion between simplified and traditional Chinese to support cross-regional search and document summarization and categorization. User studies were conducted to compare the effectiveness and efficiency of CMedPort with those of three major Chinese search engines. Results indicate that CMedPort achieved similar accuracy for search tasks, but exhibited significantly higher recall than each of the three search engines as well as higher precision than two of the search engines for browse tasks. There were no significant differences among the efficiency measures for CMedPort and benchmarks systems. A post-questionnaire regarding system usability indicated that CMedPort achieved significantly higher user satisfaction than any of the three benchmark systems. The subjects especially liked CMedPort's categorizer, commenting that it helped improve understanding of search results. These encouraging outcomes suggest a promising future for applying our approach to Internet searching and browsing in a multilingual world.
KW - Categorization
KW - Cross-regional search
KW - Information retrieval
KW - Internet searching and browsing
KW - Meta-search
KW - Search engine
KW - Summarization
UR - http://www.scopus.com/inward/record.url?scp=33750468689&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33750468689&partnerID=8YFLogxK
U2 - 10.1016/j.dss.2005.11.006
DO - 10.1016/j.dss.2005.11.006
M3 - Article
AN - SCOPUS:33750468689
SN - 0167-9236
VL - 42
SP - 1431
EP - 1448
JO - Decision Support Systems
JF - Decision Support Systems
IS - 3
ER -