@article{
 title = {Adaptive record extraction from web pages},
 type = {article},
 year = {2007},
 identifiers = {[object Object]},
 pages = {1335},
 websites = {http://portal.acm.org/citation.cfm?doid=1242572.1242838},
 publisher = {ACM Press},
 id = {668be039-8099-31c9-a7cf-dda44976f950},
 created = {2012-02-28T00:51:15.000Z},
 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 = {Park2007},
 private_publication = {false},
 abstract = {We describe an adaptive method for extracting records from web pages. Our algorithm combines a weighted tree matching metric with clustering for obtaining data extraction patterns.We compare our method experimentally to the state-of-the-art, and show that our approach is very competitive for rigidly-structured records (such as product descriptions) and far superior for loosely-structured records (such as entrieson blogs).},
 bibtype = {article},
 author = {Park, Justin and Barbosa, Denilson},
 journal = {Proceedings of the 16th international conference on World Wide Web WWW 07}
}

{"_id":"AKYA3PRqmjxBYL9Nf","bibbaseid":"park-barbosa-adaptiverecordextractionfromwebpages-2007","authorIDs":[],"author_short":["Park, J.","Barbosa, D."],"bibdata":{"title":"Adaptive record extraction from web pages","type":"article","year":"2007","identifiers":"[object Object]","pages":"1335","websites":"http://portal.acm.org/citation.cfm?doid=1242572.1242838","publisher":"ACM Press","id":"668be039-8099-31c9-a7cf-dda44976f950","created":"2012-02-28T00:51:15.000Z","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":"Park2007","private_publication":false,"abstract":"We describe an adaptive method for extracting records from web pages. Our algorithm combines a weighted tree matching metric with clustering for obtaining data extraction patterns.We compare our method experimentally to the state-of-the-art, and show that our approach is very competitive for rigidly-structured records (such as product descriptions) and far superior for loosely-structured records (such as entrieson blogs).","bibtype":"article","author":"Park, Justin and Barbosa, Denilson","journal":"Proceedings of the 16th international conference on World Wide Web WWW 07","bibtex":"@article{\n title = {Adaptive record extraction from web pages},\n type = {article},\n year = {2007},\n identifiers = {[object Object]},\n pages = {1335},\n websites = {http://portal.acm.org/citation.cfm?doid=1242572.1242838},\n publisher = {ACM Press},\n id = {668be039-8099-31c9-a7cf-dda44976f950},\n created = {2012-02-28T00:51:15.000Z},\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 = {Park2007},\n private_publication = {false},\n abstract = {We describe an adaptive method for extracting records from web pages. Our algorithm combines a weighted tree matching metric with clustering for obtaining data extraction patterns.We compare our method experimentally to the state-of-the-art, and show that our approach is very competitive for rigidly-structured records (such as product descriptions) and far superior for loosely-structured records (such as entrieson blogs).},\n bibtype = {article},\n author = {Park, Justin and Barbosa, Denilson},\n journal = {Proceedings of the 16th international conference on World Wide Web WWW 07}\n}","author_short":["Park, J.","Barbosa, D."],"urls":{"Website":"http://portal.acm.org/citation.cfm?doid=1242572.1242838"},"bibbaseid":"park-barbosa-adaptiverecordextractionfromwebpages-2007","role":"author","downloads":0,"html":""},"bibtype":"article","creationDate":"2020-02-06T23:48:12.063Z","downloads":0,"keywords":[],"search_terms":["adaptive","record","extraction","web","pages","park","barbosa"],"title":"Adaptive record extraction from web pages","year":2007}