{"id":"https://openalex.org/W2265080919","doi":"https://doi.org/10.1145/2736277.2741107","title":"Exploiting Collective Hidden Structures in Webpage Titles for Open Domain Entity Extraction","display_name":"Exploiting Collective Hidden Structures in Webpage Titles for Open Domain Entity Extraction","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W2265080919","doi":"https://doi.org/10.1145/2736277.2741107","mag":"2265080919"},"language":"en","primary_location":{"id":"doi:10.1145/2736277.2741107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th 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/A5101884750","display_name":"Wei Song","orcid":"https://orcid.org/0000-0003-2334-3623"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Song","raw_affiliation_strings":["Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101022421","display_name":"Shiqi Zhao","orcid":"https://orcid.org/0000-0002-0870-9511"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqi Zhao","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460272","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-3009-598X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677198","display_name":"Hua Wu","orcid":"https://orcid.org/0000-0002-5687-7800"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Wu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386394","display_name":"Haifeng Wang","orcid":"https://orcid.org/0000-0002-0672-7468"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]},{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China","Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626332","display_name":"Lizhen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhen Liu","raw_affiliation_strings":["Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002204887","display_name":"Hanshi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanshi Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China","Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101884750"],"corresponding_institution_ids":["https://openalex.org/I96852419"],"apc_list":null,"apc_paid":null,"fwci":3.1784,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.93096339,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1014","last_page":"1024"},"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/T10028","display_name":"Topic Modeling","score":0.9944000244140625,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9939000010490417,"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":0.8297154903411865},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.6893578767776489},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6801952123641968},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6275125741958618},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5880094170570374},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5717799067497253},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5391109585762024},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.4684869050979614},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4288179874420166},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4144662320613861},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38680189847946167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31749677658081055},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2796284854412079},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10207527875900269},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.08743393421173096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297154903411865},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.6893578767776489},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6801952123641968},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6275125741958618},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5880094170570374},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5717799067497253},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5391109585762024},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.4684869050979614},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4288179874420166},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4144662320613861},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38680189847946167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31749677658081055},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2796284854412079},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10207527875900269},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.08743393421173096},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2736277.2741107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W178774507","https://openalex.org/W205093244","https://openalex.org/W1493490255","https://openalex.org/W1505544955","https://openalex.org/W1575084925","https://openalex.org/W1974326986","https://openalex.org/W1988059434","https://openalex.org/W2024791376","https://openalex.org/W2027081355","https://openalex.org/W2045993505","https://openalex.org/W2057052429","https://openalex.org/W2068882115","https://openalex.org/W2074231493","https://openalex.org/W2093812930","https://openalex.org/W2102189859","https://openalex.org/W2113618948","https://openalex.org/W2118928552","https://openalex.org/W2126385423","https://openalex.org/W2127855221","https://openalex.org/W2129468719","https://openalex.org/W2132655161","https://openalex.org/W2137313854","https://openalex.org/W2141099517","https://openalex.org/W2142966306","https://openalex.org/W2145007893","https://openalex.org/W2148540243","https://openalex.org/W2150721933","https://openalex.org/W2153804780","https://openalex.org/W2155874911","https://openalex.org/W2163918411","https://openalex.org/W2247412337","https://openalex.org/W2471366537","https://openalex.org/W2785349534","https://openalex.org/W2998461326","https://openalex.org/W6607269496","https://openalex.org/W6608363811","https://openalex.org/W6629638141","https://openalex.org/W6630396373","https://openalex.org/W6676757265"],"related_works":["https://openalex.org/W4232403550","https://openalex.org/W623607250","https://openalex.org/W4245429118","https://openalex.org/W4205110281","https://openalex.org/W4212927854","https://openalex.org/W4211151614","https://openalex.org/W4244798043","https://openalex.org/W2469016277","https://openalex.org/W2757101400","https://openalex.org/W3102040001"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,39,60,144],"novel":[3],"method":[4,21,48,101,142,149],"for":[5],"open":[6,107],"domain":[7,108,153],"named":[8],"entity":[9],"extraction":[10],"by":[11,28],"exploiting":[12],"the":[13,23,83,117,129,138,163],"collective":[14,61],"hidden":[15,24,84],"structures":[16,26],"in":[17,59,143,156],"webpage":[18,31],"titles.":[19],"Our":[20,148],"uncovers":[22],"textual":[25],"shared":[27],"sets":[29],"of":[30,46,53,106,116,140],"titles":[32],"based":[33,81],"on":[34,82],"generalized":[35],"URL":[36],"patterns":[37],"and":[38,122,124,132,159],"multiple":[40],"sequence":[41],"alignment":[42],"technique.":[43],"The":[44,51,73,96],"highlights":[45],"our":[47,100,141],"include:":[49],"1)":[50],"boundaries":[52],"entities":[54,76,109,119,131,155],"can":[55,102,150],"be":[56],"identified":[57],"automatically":[58],"way":[62],"without":[63],"any":[64],"manually":[65],"designed":[66],"pattern,":[67],"seed":[68],"or":[69,93],"class":[70],"name.":[71],"2)":[72],"connections":[74],"between":[75],"are":[77,120],"also":[78],"discovered":[79],"naturally":[80],"structures,":[85],"which":[86],"makes":[87],"it":[88],"easy":[89],"to":[90],"incorporate":[91],"distant":[92],"weak":[94],"supervision.":[95],"experiments":[97],"show":[98,137],"that":[99],"harvest":[103],"large":[104,114],"scale":[105],"with":[110,162],"high":[111],"precision.":[112],"A":[113],"ratio":[115],"extracted":[118,130],"long-tailed":[121],"complex":[123],"cover":[125],"diverse":[126],"topics.":[127],"Given":[128],"their":[133],"connections,":[134],"we":[135],"further":[136],"effectiveness":[139],"weakly":[145],"supervised":[146],"setting.":[147],"produce":[151],"better":[152],"specific":[154],"both":[157],"precision":[158],"recall":[160],"compared":[161],"state-of-the-art":[164],"approaches.":[165]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}