{"id":"https://openalex.org/W3177052505","doi":"https://doi.org/10.1145/3464509.3464892","title":"Pre-Trained Web Table Embeddings for Table Discovery","display_name":"Pre-Trained Web Table Embeddings for Table Discovery","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3177052505","doi":"https://doi.org/10.1145/3464509.3464892","mag":"3177052505"},"language":"en","primary_location":{"id":"doi:10.1145/3464509.3464892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3464509.3464892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fourth Workshop in Exploiting AI Techniques for Data 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/A5053195307","display_name":"Michael G\u00fcnther","orcid":"https://orcid.org/0000-0002-8158-935X"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Michael G\u00fcnther","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000229374","display_name":"Maik Thiele","orcid":"https://orcid.org/0000-0002-1665-977X"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maik Thiele","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038147189","display_name":"Julius Gonsior","orcid":"https://orcid.org/0000-0002-5985-4348"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julius Gonsior","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063512642","display_name":"Wolfgang Lehner","orcid":"https://orcid.org/0000-0001-8107-2775"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Lehner","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053195307"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":0.6971,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72014004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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":0.9904000163078308,"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":0.8243744373321533},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7942713499069214},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7289256453514099},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6629562973976135},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6109010577201843},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.533681333065033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.429451584815979},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40978604555130005},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3376886248588562},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0728011429309845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8243744373321533},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7942713499069214},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7289256453514099},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6629562973976135},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6109010577201843},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.533681333065033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.429451584815979},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40978604555130005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3376886248588562},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0728011429309845},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3464509.3464892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3464509.3464892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fourth Workshop in Exploiting AI Techniques for Data Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1988217119","https://openalex.org/W2035168844","https://openalex.org/W2078206655","https://openalex.org/W2140602286","https://openalex.org/W2154851992","https://openalex.org/W2175675225","https://openalex.org/W2196674927","https://openalex.org/W2290320465","https://openalex.org/W2341748398","https://openalex.org/W2342096063","https://openalex.org/W2493916176","https://openalex.org/W2550378979","https://openalex.org/W2575118467","https://openalex.org/W2604225376","https://openalex.org/W2610751324","https://openalex.org/W2624431344","https://openalex.org/W2626778328","https://openalex.org/W2788809149","https://openalex.org/W2798649495","https://openalex.org/W2798664493","https://openalex.org/W2804241144","https://openalex.org/W2810954846","https://openalex.org/W2950133940","https://openalex.org/W2957204582","https://openalex.org/W2971681342","https://openalex.org/W3003968453","https://openalex.org/W3003988402","https://openalex.org/W3010144884","https://openalex.org/W3014813097","https://openalex.org/W3028709955","https://openalex.org/W3084237062","https://openalex.org/W3093679380","https://openalex.org/W3103177583","https://openalex.org/W3104097132","https://openalex.org/W3142774214"],"related_works":["https://openalex.org/W4288407670","https://openalex.org/W2950396480","https://openalex.org/W947140380","https://openalex.org/W2911655849","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338"],"abstract_inverted_index":{"Pre-trained":[0],"word":[1,30],"embedding":[2,31,69],"models":[3,32,88,102,111,129],"have":[4],"become":[5],"the":[6,109,131],"de-facto":[7],"standard":[8],"to":[9,43,71,114],"model":[10],"text":[11,49],"in":[12,28,51],"state-of-the-art":[13,128],"analysis":[14,57,92],"tools":[15],"and":[16,58],"frameworks.":[17],"However,":[18],"while":[19],"there":[20],"are":[21,33,53],"massive":[22],"amounts":[23],"of":[24],"textual":[25],"data":[26,91,96],"stored":[27],"tables,":[29],"usually":[34],"pre-trained":[35,73,104,116],"on":[36,46,75,94,117],"large":[37,77],"documents.":[38],"This":[39],"mismatch":[40],"can":[41,134],"lead":[42],"narrowed":[44],"performance":[45],"tasks":[47,60,93,133],"where":[48],"values":[50],"tables":[52],"analyzed.":[54],"To":[55],"improve":[56],"retrieval":[59],"working":[61],"with":[62],"tabular":[63],"data,":[64],"we":[65,85,120],"propose":[66],"a":[67,76],"novel":[68],"technique":[70],"be":[72,135],"directly":[74],"Web":[78,105,125],"table":[79,106,126],"corpus.":[80],"In":[81],"an":[82],"experimental":[83],"evaluation,":[84],"employ":[86],"our":[87],"for":[89,130],"various":[90],"different":[95],"sources.":[97],"Our":[98],"evaluation":[99],"shows":[100],"that":[101,122],"using":[103,124],"embeddings":[107,115,127],"outperform":[108],"same":[110],"when":[112],"applied":[113],"text.":[118],"Moreover,":[119],"show":[121],"by":[123],"investigated":[132],"outperformed.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}