{"id":"https://openalex.org/W2152997076","doi":"https://doi.org/10.1145/2505515.2505602","title":"Identifying salient entities in web pages","display_name":"Identifying salient entities in web pages","publication_year":2013,"publication_date":"2013-10-27","ids":{"openalex":"https://openalex.org/W2152997076","doi":"https://doi.org/10.1145/2505515.2505602","mag":"2152997076"},"language":"en","primary_location":{"id":"doi:10.1145/2505515.2505602","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge 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/A5067778879","display_name":"Michael Gamon","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Gamon","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070657152","display_name":"Tae Yano","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tae Yano","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102246878","display_name":"Xinying Song","orcid":"https://orcid.org/0009-0002-9445-0717"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinying Song","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026794270","display_name":"Johnson Apacible","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johnson Apacible","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041476585","display_name":"Patrick Pantel","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Pantel","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067778879"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":6.9214,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96706258,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2375","last_page":"2380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8448292016983032},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6868489980697632},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5990593433380127},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5599213242530823},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.5074343085289001},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.47163793444633484},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.42634376883506775},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4252791106700897},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.4151570200920105},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4126688539981842},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3072585463523865},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.2648776173591614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1821126639842987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8448292016983032},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6868489980697632},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5990593433380127},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5599213242530823},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.5074343085289001},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.47163793444633484},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.42634376883506775},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4252791106700897},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.4151570200920105},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4126688539981842},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3072585463523865},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.2648776173591614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1821126639842987},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2505515.2505602","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.914.9826","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.914.9826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.patrickpantel.com/download/papers/2013/cikm13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W90502410","https://openalex.org/W172325362","https://openalex.org/W1532325895","https://openalex.org/W1566513354","https://openalex.org/W1678356000","https://openalex.org/W1809222622","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W1983578042","https://openalex.org/W2008652694","https://openalex.org/W2040419587","https://openalex.org/W2046983134","https://openalex.org/W2047221353","https://openalex.org/W2049711652","https://openalex.org/W2051082414","https://openalex.org/W2064418625","https://openalex.org/W2074886252","https://openalex.org/W2091661144","https://openalex.org/W2101390659","https://openalex.org/W2115346359","https://openalex.org/W2123086176","https://openalex.org/W2134131174","https://openalex.org/W2136504847","https://openalex.org/W2145122158","https://openalex.org/W2149469409","https://openalex.org/W2152314154","https://openalex.org/W2156577800","https://openalex.org/W2165612380","https://openalex.org/W2167859982","https://openalex.org/W2182143093","https://openalex.org/W3088311774","https://openalex.org/W4285719527","https://openalex.org/W6681418076","https://openalex.org/W6784437298"],"related_works":["https://openalex.org/W2064945795","https://openalex.org/W2156420263","https://openalex.org/W2088345472","https://openalex.org/W2095105111","https://openalex.org/W2534595131","https://openalex.org/W4385753583","https://openalex.org/W182781187","https://openalex.org/W2008577673","https://openalex.org/W2109933404","https://openalex.org/W2092706362"],"abstract_inverted_index":{"We":[0,53,77,123,148],"propose":[1,78],"a":[2,33,59,66,93,104,110,131,137,171],"system":[3,60],"that":[4,61,82,108,150],"determines":[5],"the":[6,21,41,74,100,145,158,162,166],"salience":[7,79],"of":[8,23,36,112,127,161],"entities":[9,24,37],"within":[10],"web":[11,26,67,89,95,120],"documents.":[12],"Many":[13],"recent":[14],"advances":[15],"in":[16,25,119],"commercial":[17],"search":[18,90,121],"engines":[19],"leverage":[20],"identification":[22],"pages.":[27],"However,":[28],"for":[29,49],"many":[30],"pages,":[31],"only":[32],"small":[34],"subset":[35],"are":[38],"central":[39],"to":[40,46,70,73,144,170],"document,":[42],"which":[43,140],"can":[44],"lead":[45],"degraded":[47],"relevance":[48],"entity":[50,64],"triggered":[51],"experiences.":[52],"address":[54],"this":[55],"problem":[56],"by":[57],"devising":[58],"scores":[62],"each":[63],"on":[65,115],"page":[68,75],"according":[69],"its":[71],"centrality":[72],"content.":[76],"classification":[80],"functions":[81],"incorporate":[83],"various":[84],"cues":[85],"from":[86],"document":[87],"content,":[88],"logs,":[91],"and":[92,157],"large":[94],"graph.":[96],"To":[97],"cost-effectively":[98],"train":[99],"models,":[101],"we":[102,141],"introduce":[103],"soft":[105],"labeling":[106],"methodology":[107],"generates":[109],"set":[111],"annotations":[113],"based":[114],"user":[116],"behaviors":[117],"observed":[118],"logs.":[122],"evaluate":[124],"several":[125],"variations":[126],"our":[128,151],"model":[129],"via":[130],"large-scale":[132],"empirical":[133],"study":[134],"conducted":[135],"over":[136],"test":[138],"set,":[139],"release":[142],"publicly":[143],"research":[146],"community.":[147],"demonstrate":[149],"methods":[152],"significantly":[153],"outperform":[154],"competitive":[155],"baselines":[156],"previous":[159],"state":[160],"art,":[163],"while":[164],"keeping":[165],"human":[167],"annotation":[168],"cost":[169],"minimum.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}