Categorizing Unknown Text Patterns for Information Extraction Using a Search Result Mining Approach

Categorizing Unknown Text Patterns for Information Extraction Using a Search Result Mining Approach. Huang, C., Chuang, S., & Chien, L. In IJCNLP, 2001.
abstract bibtex

An advanced information extraction system requires an effective text categorization technique to categorize extracted facts (text patterns) into a hierarchy of domain-specific topic categories. Text patterns are often short and their categorization is quite different from conventional document categorization. This paper proposes a Web mining approach that exploits Web resources to categorize unknown text patterns with limited manual intervention. The feasibility and wide adaptability of the proposed approach has been shown with extensive experiments on categorizing different kinds of text patterns including domain-specific terms, named entities, and even paper titles into Yahoo!’s taxonomy trees.

@inProceedings{
 title = {Categorizing Unknown Text Patterns for Information Extraction Using a Search Result Mining Approach},
 type = {inProceedings},
 year = {2001},
 id = {e33c8c73-3588-39c7-8e2b-ba0ef91cafdd},
 created = {2011-01-29T09:23:47.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Huang2001},
 private_publication = {false},
 abstract = {An advanced information extraction system requires an effective text categorization technique to categorize extracted facts (text patterns) into a hierarchy of domain-specific topic categories. Text patterns are often short and their categorization is quite different from conventional document categorization. This paper proposes a Web mining approach that exploits Web resources to categorize unknown text patterns with limited manual intervention. The feasibility and wide adaptability of the proposed approach has been shown with extensive experiments on categorizing different kinds of text patterns including domain-specific terms, named entities, and even paper titles into Yahoo!’s taxonomy trees.},
 bibtype = {inProceedings},
 author = {Huang, Chien-Chung and Chuang, Shui-Lung and Chien, Lee-Feng},
 booktitle = {IJCNLP}
}

Downloads: 0

{"_id":"mgySd2B34mpXHF7rA","bibbaseid":"huang-chuang-chien-categorizingunknowntextpatternsforinformationextractionusingasearchresultminingapproach-2001","authorIDs":[],"author_short":["Huang, C.","Chuang, S.","Chien, L."],"bibdata":{"title":"Categorizing Unknown Text Patterns for Information Extraction Using a Search Result Mining Approach","type":"inProceedings","year":"2001","id":"e33c8c73-3588-39c7-8e2b-ba0ef91cafdd","created":"2011-01-29T09:23:47.000Z","file_attached":false,"profile_id":"5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6","group_id":"066b42c8-f712-3fc3-abb2-225c158d2704","last_modified":"2017-03-14T14:36:19.698Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Huang2001","private_publication":false,"abstract":"An advanced information extraction system requires an effective text categorization technique to categorize extracted facts (text patterns) into a hierarchy of domain-specific topic categories. Text patterns are often short and their categorization is quite different from conventional document categorization. This paper proposes a Web mining approach that exploits Web resources to categorize unknown text patterns with limited manual intervention. The feasibility and wide adaptability of the proposed approach has been shown with extensive experiments on categorizing different kinds of text patterns including domain-specific terms, named entities, and even paper titles into Yahoo!’s taxonomy trees.","bibtype":"inProceedings","author":"Huang, Chien-Chung and Chuang, Shui-Lung and Chien, Lee-Feng","booktitle":"IJCNLP","bibtex":"@inProceedings{\n title = {Categorizing Unknown Text Patterns for Information Extraction Using a Search Result Mining Approach},\n type = {inProceedings},\n year = {2001},\n id = {e33c8c73-3588-39c7-8e2b-ba0ef91cafdd},\n created = {2011-01-29T09:23:47.000Z},\n file_attached = {false},\n profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},\n group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},\n last_modified = {2017-03-14T14:36:19.698Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Huang2001},\n private_publication = {false},\n abstract = {An advanced information extraction system requires an effective text categorization technique to categorize extracted facts (text patterns) into a hierarchy of domain-specific topic categories. Text patterns are often short and their categorization is quite different from conventional document categorization. This paper proposes a Web mining approach that exploits Web resources to categorize unknown text patterns with limited manual intervention. The feasibility and wide adaptability of the proposed approach has been shown with extensive experiments on categorizing different kinds of text patterns including domain-specific terms, named entities, and even paper titles into Yahoo!’s taxonomy trees.},\n bibtype = {inProceedings},\n author = {Huang, Chien-Chung and Chuang, Shui-Lung and Chien, Lee-Feng},\n booktitle = {IJCNLP}\n}","author_short":["Huang, C.","Chuang, S.","Chien, L."],"bibbaseid":"huang-chuang-chien-categorizingunknowntextpatternsforinformationextractionusingasearchresultminingapproach-2001","role":"author","urls":{},"downloads":0,"html":""},"bibtype":"inProceedings","creationDate":"2020-02-06T23:48:11.709Z","downloads":0,"keywords":[],"search_terms":["categorizing","unknown","text","patterns","information","extraction","using","search","result","mining","approach","huang","chuang","chien"],"title":"Categorizing Unknown Text Patterns for Information Extraction Using a Search Result Mining Approach","year":2001}