{"id":"https://openalex.org/W2154806926","doi":"https://doi.org/10.1109/iri.2011.6009551","title":"How do they compare? Automatic identification of comparable entities on the Web","display_name":"How do they compare? Automatic identification of comparable entities on the Web","publication_year":2011,"publication_date":"2011-08-01","ids":{"openalex":"https://openalex.org/W2154806926","doi":"https://doi.org/10.1109/iri.2011.6009551","mag":"2154806926"},"language":"en","primary_location":{"id":"doi:10.1109/iri.2011.6009551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2011.6009551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Information Reuse &amp; Integration","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/A5110209854","display_name":"Alpa Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alpa Jain","raw_affiliation_strings":["Yahoo Research Laboratories, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo Research Laboratories, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041476585","display_name":"Patrick Pantel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Pantel","raw_affiliation_strings":["Yahoo Research Laboratories, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo Research Laboratories, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110209854"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":2.2169,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91285545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"21","issue":null,"first_page":"228","last_page":"233"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9901999831199646,"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/T11719","display_name":"Data Quality and Management","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7460974454879761},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6721833348274231},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34740352630615234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460974454879761},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6721833348274231},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34740352630615234},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iri.2011.6009551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2011.6009551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Information Reuse &amp; Integration","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W17814598","https://openalex.org/W158294556","https://openalex.org/W197270748","https://openalex.org/W1484050045","https://openalex.org/W1500117362","https://openalex.org/W1578697867","https://openalex.org/W1593045043","https://openalex.org/W1601974683","https://openalex.org/W1956559956","https://openalex.org/W1988931981","https://openalex.org/W2005646337","https://openalex.org/W2050712820","https://openalex.org/W2103296194","https://openalex.org/W2103931177","https://openalex.org/W2108745425","https://openalex.org/W2113958117","https://openalex.org/W2115461474","https://openalex.org/W2117400858","https://openalex.org/W2142305207","https://openalex.org/W2158188757","https://openalex.org/W2159637323","https://openalex.org/W2166776180","https://openalex.org/W2882319491","https://openalex.org/W2920277907","https://openalex.org/W4206165639","https://openalex.org/W6600736262","https://openalex.org/W6608048608","https://openalex.org/W6628906816","https://openalex.org/W6636170422","https://openalex.org/W6677437730","https://openalex.org/W6683226453"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"People":[0],"love":[1],"comparing":[2],"things:":[3],"from":[4,87],"home":[5],"mortgages":[6],"and":[7,13,46,91,107,125,127,167,176],"digital":[8],"cameras":[9],"to":[10,21,28,54,63,144],"travel":[11],"destinations":[12],"political":[14],"philosophies.":[15],"Today,":[16],"we":[17,68,99],"are":[18,134],"mostly":[19],"limited":[20],"browsing":[22],"documents":[23],"after":[24],"issuing":[25],"comparative":[26,77],"queries":[27],"Web":[29,94,130,145],"search":[30,57,88,131],"engines,":[31],"such":[32,140],"as":[33,142],"\u201c15-year":[34],"vs.":[35,48],"30-year":[36],"mortgage\u201d,":[37],"\u201cNikon":[38],"D90":[39],"/":[40],"Canon":[41],"40D\u201d,":[42],"\u201cOahu":[43],"or":[44],"Maui\u201d,":[45],"\u201ccommunism":[47],"fascism\u201d.":[49],"There":[50],"is":[51],"an":[52,112],"opportunity":[53],"improve":[55],"the":[56,155],"experience":[58],"by":[59,79,164],"automatically":[60],"offering":[61],"comparisons":[62],"users.":[64],"In":[65],"this":[66,74],"paper,":[67],"propose":[69],"a":[70,81,92,135,169,177],"first":[71],"step":[72],"towards":[73],"goal":[75],"of":[76,84,157,171,179],"analysis":[78,115],"mining":[80,139],"broad":[82],"class":[83],"comparable":[85],"entities":[86,141],"query":[89,132],"logs":[90,133],"large":[93],"crawl.":[95],"Example":[96],"comparables":[97,121],"that":[98,117,129],"extract":[100],"include":[101],"medicines,":[102],"appliances,":[103],"electronics,":[104],"vacation":[105],"destinations,":[106],"many":[108],"more.":[109],"We":[110,152],"present":[111],"extensive":[113],"empirical":[114],"showing":[116,128],"our":[118,158],"methods":[119,159],"generate":[120],"with":[122,160],"high":[123],"precision":[124,175],"recall,":[126],"superior":[136],"source":[137],"for":[138,149],"compared":[143],"pages,":[146],"typically":[147],"used":[148],"extraction":[150],"tasks.":[151],"further":[153],"compare":[154],"performance":[156],"\u201crelated":[161],"entities\u201d":[162],"reported":[163],"Google":[165],"Sets,":[166],"show":[168],"gain":[170,178],"39%":[172],"in":[173,181],"average":[174],"30%":[180],"NCDG.":[182]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
