{"id":"https://openalex.org/W2102261150","doi":"https://doi.org/10.1145/1031453.1031478","title":"Stylistic and lexical co-training for web block classification","display_name":"Stylistic and lexical co-training for web block classification","publication_year":2004,"publication_date":"2004-11-12","ids":{"openalex":"https://openalex.org/W2102261150","doi":"https://doi.org/10.1145/1031453.1031478","mag":"2102261150"},"language":"en","primary_location":{"id":"doi:10.1145/1031453.1031478","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031453.1031478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024845834","display_name":"Chee How Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chee How Lee","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066305082","display_name":"Min\u2010Yen Kan","orcid":"https://orcid.org/0000-0001-8507-3716"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Min-Yen Kan","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072213487","display_name":"Sandra Lai","orcid":"https://orcid.org/0000-0003-4198-9989"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sandra Lai","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2307,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9314557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8292677402496338},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6521338820457458},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6164493560791016},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5956620573997498},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4480859339237213},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.42765510082244873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41626057028770447},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.41279157996177673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37389546632766724},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35977792739868164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292677402496338},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6521338820457458},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6164493560791016},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5956620573997498},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4480859339237213},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.42765510082244873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41626057028770447},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.41279157996177673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37389546632766724},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35977792739868164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1031453.1031478","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031453.1031478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/41312","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/41312","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.103.1978","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.103.1978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~kanmy/papers/p53-how.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W126367074","https://openalex.org/W1978394996","https://openalex.org/W2037603696","https://openalex.org/W2048679005","https://openalex.org/W2053463056","https://openalex.org/W2064716575","https://openalex.org/W2064818667","https://openalex.org/W2088854903","https://openalex.org/W2093559286","https://openalex.org/W2105102731","https://openalex.org/W2126024570","https://openalex.org/W2129595335","https://openalex.org/W2141765212","https://openalex.org/W2167859982","https://openalex.org/W2169899598"],"related_works":["https://openalex.org/W2397288865","https://openalex.org/W2368524271","https://openalex.org/W4247116873","https://openalex.org/W2576709312","https://openalex.org/W2023657818","https://openalex.org/W2392797073","https://openalex.org/W2384907669","https://openalex.org/W2611741382","https://openalex.org/W2083329789","https://openalex.org/W2376574812"],"abstract_inverted_index":{"Many":[0],"applications":[1],"which":[2,75],"use":[3],"web":[4,16,20,54],"data":[5],"extract":[6],"information":[7],"from":[8],"a":[9,15,32,103,111],"limited":[10],"number":[11],"of":[12,52,105],"regions":[13],"on":[14,46,62,79],"page.":[17,55],"As":[18],"such,":[19],"page":[21],"division":[22],"into":[23],"blocks":[24],"and":[25,49,81,114],"the":[26,53,70,98],"subsequent":[27],"block":[28],"classification":[29,44,61],"have":[30],"become":[31],"preprocessing":[33],"step.":[34],"We":[35],"introduce":[36],"PARCELS,":[37],"an":[38],"open-source,":[39],"co-trained":[40],"approach":[41,117],"that":[42,97,115],"performs":[43,60],"based":[45,78],"separate":[47],"stylistic":[48,86],"lexical":[50],"views":[51],"Unlike":[56],"previous":[57],"work,":[58],"PARCELS":[59],"fine-grained":[63],"blocks.":[64],"In":[65],"addition":[66],"to":[67,120],"table-based":[68],"layout,":[69],"system":[71],"handles":[72],"real-world":[73],"pages":[74,89],"feature":[76],"layout":[77],"divisions":[80],"spans":[82],"as":[83,85],"well":[84],"inference":[87],"for":[88],"using":[90],"cascaded":[91],"style":[92],"sheets.":[93],"Our":[94],"evaluation":[95],"shows":[96],"co-training":[99],"process":[100],"results":[101],"in":[102,107],"reduction":[104],"28.5%":[106],"error":[108],"rate":[109],"over":[110],"single-view":[112],"classifier":[113],"our":[116],"is":[118],"comparable":[119],"other":[121],"state-of-the-art":[122],"systems.":[123]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}