{"id":"https://openalex.org/W2165321084","doi":"https://doi.org/10.1145/1772690.1772791","title":"Automatic extraction of clickable structured web contents for name entity queries","display_name":"Automatic extraction of clickable structured web contents for name entity queries","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W2165321084","doi":"https://doi.org/10.1145/1772690.1772791","mag":"2165321084"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772791","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","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/A5111954563","display_name":"Xiaoxin Yin","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":"Xiaoxin Yin","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081955607","display_name":"Wenzhao Tan","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":"Wenzhao Tan","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418684","display_name":"Xiaoli Li","orcid":"https://orcid.org/0000-0002-0762-6562"},"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":"Xiao Li","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010761395","display_name":"Yi-Chin Tu","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":"Yi-Chin Tu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111954563"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":3.5708,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94390144,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"991","last_page":"1000"},"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/T12285","display_name":"Surface Chemistry and Catalysis","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9872999787330627,"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":0.856930136680603},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7204658389091492},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6303618550300598},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5904252529144287},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5881997346878052},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5594044923782349},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5592479705810547},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5241061449050903},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4748407006263733},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4150213301181793},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.4144437909126282},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.34327274560928345},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.2860393226146698},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20585501194000244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.856930136680603},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7204658389091492},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6303618550300598},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5904252529144287},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5881997346878052},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5594044923782349},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5592479705810547},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5241061449050903},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4748407006263733},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4150213301181793},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.4144437909126282},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.34327274560928345},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.2860393226146698},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20585501194000244},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1772690.1772791","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.8520","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.8520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/120887/fp0254-yin.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.658.7019","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.658.7019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ra.ethz.ch/CDstore/www2010/www/p991.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1493490255","https://openalex.org/W1553019137","https://openalex.org/W2003684739","https://openalex.org/W2005646337","https://openalex.org/W2015551056","https://openalex.org/W2050078085","https://openalex.org/W2098700435","https://openalex.org/W2104086170","https://openalex.org/W2118388899","https://openalex.org/W2133156844","https://openalex.org/W2140116426","https://openalex.org/W2143309843","https://openalex.org/W2150721933","https://openalex.org/W2153072229","https://openalex.org/W2154455818","https://openalex.org/W2155160033","https://openalex.org/W2160196229","https://openalex.org/W2163375626","https://openalex.org/W2165922980","https://openalex.org/W2169463693","https://openalex.org/W2170363795","https://openalex.org/W2171364811","https://openalex.org/W4285719527","https://openalex.org/W6821143472"],"related_works":["https://openalex.org/W1979144454","https://openalex.org/W182781187","https://openalex.org/W4385753583","https://openalex.org/W2008577673","https://openalex.org/W77836141","https://openalex.org/W2092706362","https://openalex.org/W1486482441","https://openalex.org/W2023856424","https://openalex.org/W2377634017","https://openalex.org/W2146357243"],"abstract_inverted_index":{"Today":[0],"the":[1,35,45,63,116],"major":[2],"web":[3,66,93,142,171,174,198],"search":[4,53,175,181],"engines":[5],"answer":[6,41],"queries":[7,42,160],"by":[8,18,43],"showing":[9,44],"ten":[10],"result":[11],"snippets,":[12],"which":[13,227],"need":[14],"to":[15,30,39,80,123,136,214],"be":[16],"inspected":[17],"users":[19],"for":[20,97,109,144,155,159,200],"identifying":[21],"relevant":[22],"results.":[23],"In":[24],"this":[25],"paper":[26],"we":[27,75],"investigate":[28],"how":[29],"extract":[31,84,137],"structured":[32,85,138,157,194],"information":[33,77,139,158,195,208],"from":[34,126,140,173,179,188,196],"web,":[36],"in":[37],"order":[38],"directly":[40],"contents":[46,67],"being":[47],"searched":[48],"for.":[49],"We":[50,148,223],"treat":[51],"users'":[52,180],"trails":[54],"(i.e.,":[55],"post-search":[56],"browsing":[57],"behaviors)":[58],"as":[59],"implicit":[60,131],"labels":[61,74],"on":[62,72,207],"relevance":[64],"between":[65],"and":[68,83,112,133,192,233],"user":[69,190],"queries.":[70],"Based":[71],"such":[73],"use":[76,134],"extraction":[78],"approach":[79],"build":[81,124,177],"wrappers":[82,125,178,186],"information.":[86],"An":[87],"important":[88,170],"observation":[89],"is":[90],"that":[91],"many":[92,141],"sites":[94,172,199],"contain":[95],"pages":[96,114,143],"name":[98,146,162],"entities":[99,163],"of":[100,130,164],"certain":[101,165],"categories":[102],"(e.g.,":[103],"AOL":[104],"Music":[105],"contains":[106],"a":[107,127,151],"page":[108],"each":[110,201],"musician),":[111],"these":[113],"have":[115],"same":[117],"format.":[118],"This":[119],"makes":[120],"it":[121],"possible":[122],"small":[128],"amount":[129],"labels,":[132],"them":[135],"different":[145,197],"entities.":[147],"propose":[149],"STRUCLICK,":[150],"fully":[152],"automated":[153],"system":[154],"extracting":[156],"containing":[161],"categories.":[166],"It":[167],"can":[168,211],"identify":[169],"logs,":[176],"trails,":[182],"filter":[183],"out":[184],"bad":[185],"built":[187],"random":[189],"clicks,":[191],"combine":[193],"query.":[202],"Comparing":[203],"with":[204],"existing":[205],"approaches":[206],"extraction,":[209],"STRUCLICK":[210,229],"assign":[212],"semantics":[213],"extracted":[215],"data":[216],"without":[217],"any":[218],"human":[219],"labeling":[220],"or":[221],"supervision.":[222],"perform":[224],"comprehensive":[225],"experiments,":[226],"show":[228],"achieves":[230],"high":[231],"accuracy":[232],"good":[234],"scalability.":[235]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
