{"id":"https://openalex.org/W2007442002","doi":"https://doi.org/10.1145/1316902.1316920","title":"Adaptive web-page content identification","display_name":"Adaptive web-page content identification","publication_year":2007,"publication_date":"2007-11-09","ids":{"openalex":"https://openalex.org/W2007442002","doi":"https://doi.org/10.1145/1316902.1316920","mag":"2007442002"},"language":"en","primary_location":{"id":"doi:10.1145/1316902.1316920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1316902.1316920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103247706","display_name":"John Gibson","orcid":"https://orcid.org/0000-0003-1731-4869"},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Gibson","raw_affiliation_strings":["The MITRE Corporation, Bedford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, Bedford, MA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011679042","display_name":"Ben Wellner","orcid":"https://orcid.org/0000-0003-2689-990X"},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Wellner","raw_affiliation_strings":["The MITRE Corporation, Bedford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, Bedford, MA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009321626","display_name":"Susan Lubar","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susan Lubar","raw_affiliation_strings":["The MITRE Corporation, Bedford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, Bedford, MA","institution_ids":["https://openalex.org/I44896327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44896327"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9909999966621399,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9516000151634216,"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/conditional-random-field","display_name":"Conditional random field","score":0.8188542127609253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8150841593742371},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7392320036888123},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6962379217147827},{"id":"https://openalex.org/keywords/dynamic-web-page","display_name":"Dynamic web page","score":0.5674067139625549},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49406197667121887},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48920559883117676},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.48641490936279297},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47581058740615845},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4317641258239746},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.42822664976119995},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4201485514640808},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.41255003213882446},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.4124874174594879},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.40919312834739685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32128506898880005},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11942577362060547}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8188542127609253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150841593742371},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7392320036888123},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6962379217147827},{"id":"https://openalex.org/C100158260","wikidata":"https://www.wikidata.org/wiki/Q1650567","display_name":"Dynamic web page","level":3,"score":0.5674067139625549},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49406197667121887},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48920559883117676},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.48641490936279297},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47581058740615845},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4317641258239746},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.42822664976119995},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4201485514640808},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.41255003213882446},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.4124874174594879},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.40919312834739685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32128506898880005},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11942577362060547},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1316902.1316920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1316902.1316920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:ADA470494","is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&amp;verb=getRecord&amp;metadataPrefix=html&amp;identifier=ADA470494","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","issn_l":null,"issn":null,"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":"DTIC","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.465.6886","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.465.6886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dtic.mil/dtic/tr/fulltext/u2/a470494.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.99.5823","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.99.5823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mitre.org/work/tech_papers/tech_papers_07/07_0958/07_0958.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1500874501","https://openalex.org/W1985085323","https://openalex.org/W2005646337","https://openalex.org/W2034797903","https://openalex.org/W2038124402","https://openalex.org/W2087406717","https://openalex.org/W2110203774","https://openalex.org/W2135479443","https://openalex.org/W2147880316","https://openalex.org/W2153072229","https://openalex.org/W2156515921","https://openalex.org/W2158188757","https://openalex.org/W2177750903","https://openalex.org/W2757814986"],"related_works":["https://openalex.org/W2368657441","https://openalex.org/W2389737178","https://openalex.org/W2369026424","https://openalex.org/W2394263969","https://openalex.org/W2167278502","https://openalex.org/W406631474","https://openalex.org/W2077831857","https://openalex.org/W2049949118","https://openalex.org/W2346384915","https://openalex.org/W2944520697"],"abstract_inverted_index":{"Identifying":[0],"which":[1],"parts":[2],"of":[3,12,82,94,127,132,144,149],"a":[4,23,83,98,102,114],"Web-page":[5],"contain":[6],"target":[7],"content":[8,73,96,125],"(e.g.,":[9],"the":[10,19,47,80,92,124,133,142,150],"portion":[11,126],"an":[13],"online":[14],"news":[15],"page":[16],"that":[17,26],"contains":[18],"actual":[20],"article)":[21],"is":[22],"significant":[24],"problem":[25,38,93,104],"must":[27],"be":[28],"addressed":[29],"for":[30,51],"many":[31],"Web-based":[32],"applications.":[33],"Most":[34],"approaches":[35],"to":[36,45,61,70],"this":[37,88],"involve":[39],"crafting":[40],"hand-tailored":[41],"rules":[42],"or":[43],"scripts":[44],"extract":[46,72],"content,":[48],"customized":[49],"separately":[50],"particular":[52],"Web":[53],"sites.":[54],"Besides":[55],"requiring":[56],"considerable":[57],"time":[58,134],"and":[59,77,109,147],"effort":[60],"implement,":[62],"hand-built":[63],"extraction":[64],"routines":[65],"are":[66],"brittle:":[67],"they":[68],"fail":[69],"properly":[71],"in":[74,106],"some":[75],"cases":[76],"break":[78],"when":[79],"structure":[81,105],"site's":[84],"Web-pages":[85],"changes.":[86],"In":[87],"work":[89],"we":[90,121],"treat":[91],"identifying":[95],"as":[97,140],"sequence":[99,118],"labeling":[100,119],"problem,":[101],"common":[103],"machine":[107],"learning":[108],"natural":[110],"language":[111],"processing.":[112],"Using":[113],"Conditional":[115],"Random":[116],"Field":[117],"model,":[120],"correctly":[122],"identify":[123],"web-pages":[128],"anywhere":[129],"from":[130],"80-97%":[131],"depending":[135],"on":[136],"experimental":[137],"factors":[138],"such":[139],"ensuring":[141],"absence":[143],"duplicate":[145],"documents":[146],"application":[148],"model":[151],"against":[152],"unseen":[153],"sources.":[154]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
