{"id":"https://openalex.org/W3197320265","doi":"https://doi.org/10.1007/978-3-030-88361-4_20","title":"Dataset or Not? A Study on the Veracity of Semantic Markup for Dataset Pages","display_name":"Dataset or Not? A Study on the Veracity of Semantic Markup for Dataset Pages","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3197320265","doi":"https://doi.org/10.1007/978-3-030-88361-4_20","mag":"3197320265"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-88361-4_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-88361-4_20","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-88361-4_20.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-88361-4_20.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008176418","display_name":"Tarfah Alrashed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tarfah Alrashed","raw_affiliation_strings":["CSAIL, MIT, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, Cambridge, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084443795","display_name":"Dimitris Paparas","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitris Paparas","raw_affiliation_strings":["Google Research, Google, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Google, New York, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103212061","display_name":"Omar Benjelloun","orcid":"https://orcid.org/0000-0002-4173-7709"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omar Benjelloun","raw_affiliation_strings":["Google Research, Google, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Google, New York, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102900861","display_name":"Ying Sheng","orcid":"https://orcid.org/0000-0003-4561-2097"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Sheng","raw_affiliation_strings":["Google Research, Google, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Google, New York, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041421536","display_name":"Natasha Noy","orcid":"https://orcid.org/0000-0002-7437-0624"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natasha Noy","raw_affiliation_strings":["Google Research, Google, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Google, New York, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":1.7953,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87354435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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/T11719","display_name":"Data Quality and Management","score":0.9965000152587891,"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":0.8811239004135132},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.8222467303276062},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.698672890663147},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5882362723350525},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48925089836120605},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.44567206501960754},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4102972447872162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33805856108665466},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.1670530140399933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8811239004135132},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.8222467303276062},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.698672890663147},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5882362723350525},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48925089836120605},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.44567206501960754},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4102972447872162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33805856108665466},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.1670530140399933}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-88361-4_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-88361-4_20","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-88361-4_20.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-88361-4_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-88361-4_20","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-88361-4_20.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197320265.pdf","grobid_xml":"https://content.openalex.org/works/W3197320265.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W109245773","https://openalex.org/W2055886766","https://openalex.org/W2059586463","https://openalex.org/W2084975492","https://openalex.org/W2140730091","https://openalex.org/W2152805927","https://openalex.org/W2157583440","https://openalex.org/W2160024037","https://openalex.org/W2166601255","https://openalex.org/W2166706824","https://openalex.org/W2196674927","https://openalex.org/W2610332888","https://openalex.org/W2799037506","https://openalex.org/W2914479823","https://openalex.org/W2926805670","https://openalex.org/W2950860947","https://openalex.org/W2964091842","https://openalex.org/W2969723769","https://openalex.org/W2971262600","https://openalex.org/W2982150889","https://openalex.org/W3006502835","https://openalex.org/W3081176230","https://openalex.org/W3099461227","https://openalex.org/W3102654612","https://openalex.org/W3108941002","https://openalex.org/W4255399413"],"related_works":["https://openalex.org/W2042562985","https://openalex.org/W183683573","https://openalex.org/W2561743279","https://openalex.org/W2139931245","https://openalex.org/W3021385460","https://openalex.org/W2477306097","https://openalex.org/W1566994962","https://openalex.org/W2178182010","https://openalex.org/W2362437884","https://openalex.org/W1559346900"],"abstract_inverted_index":{"Abstract":[0],"Semantic":[1],"markup,":[2],"such":[3],"as":[4],",":[5],"allows":[6],"providers":[7],"on":[8,42,52,69,78],"the":[9,59,70,87,103,122,149,152,181,194,202],"Web":[10],"to":[11,34,40,44,79,101,146,192,200,204,209],"describe":[12,83,118],"content":[13],"using":[14],"a":[15,25,63,144,158,167,172],"shared":[16],"controlled":[17],"vocabulary.":[18],"This":[19,185],"markup":[20,54,114,126,137,170,198],"is":[21,138,171],"invaluable":[22],"in":[23,37,58,196],"enabling":[24,89],"broad":[26],"range":[27],"of":[28,61,109,124,151,187],"applications,":[29],"from":[30,107],"vertical":[31,64,93],"search":[32,38,65],"engines,":[33],"rich":[35],"snippets":[36],"results,":[39],"actions":[41],"emails,":[43],"many":[45],"others.":[46],"In":[47],"this":[48,92,136],"paper,":[49],"we":[50,95,99],"focus":[51],"semantic":[53,197],"for":[55,67,91,127],"datasets,":[56],"specifically":[57],"context":[60],"developing":[62,157],"engine":[66],"datasets":[68],"Web,":[71],"Google\u2019s":[72],"Dataset":[73,75,128,190],"Search.":[74],"Search":[76,191],"relies":[77],"identify":[80],"pages":[81,106,134],"that":[82,98,112,162],"datasets.":[84,119],"While":[85],"was":[86],"core":[88],"technology":[90],"search,":[94],"also":[96],"discovered":[97],"need":[100],"address":[102],"following":[104],"problem:":[105],"61%":[108],"internet":[110],"hosts":[111],"provide":[113,205],"do":[115],"not":[116,139,166],"actually":[117],"We":[120,141],"analyze":[121],"veracity":[123],"dataset":[125,153,173],"Search\u2019s":[129],"Web-scale":[130],"corpus":[131,155],"and":[132,199],"categorize":[133],"where":[135],"reliable.":[140],"then":[142],"propose":[143],"way":[145],"drastically":[147],"increase":[148],"quality":[150,207],"metadata":[154,203],"by":[156],"deep":[159],"neural-network":[160],"classifier":[161,176],"identifies":[163],"whether":[164],"or":[165],"page":[168],"with":[169],"page.":[174],"Our":[175],"achieves":[177],"96.7%":[178],"recall":[179],"at":[180],"95%":[182],"precision":[183,188],"point.":[184],"level":[186],"enables":[189],"circumvent":[193],"noise":[195],"use":[201],"high":[206],"results":[208],"users.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}