{"id":"https://openalex.org/W2062783131","doi":"https://doi.org/10.1145/1871437.1871633","title":"A fine-grained taxonomy of tables on the web","display_name":"A fine-grained taxonomy of tables on the web","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2062783131","doi":"https://doi.org/10.1145/1871437.1871633","mag":"2062783131"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871633","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871633","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 ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5066954331","display_name":"Eric Crestan","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":"Eric Crestan","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., 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/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":"Patrick Pantel","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6565,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.70242384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1405","last_page":"1408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9750999808311462,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9742000102996826,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.820561408996582},{"id":"https://openalex.org/keywords/disk-formatting","display_name":"Disk formatting","score":0.8010213375091553},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.7473893165588379},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.670862078666687},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4933718740940094},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.46880534291267395},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3393487334251404},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3272938132286072},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32557791471481323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820561408996582},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.8010213375091553},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.7473893165588379},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.670862078666687},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4933718740940094},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.46880534291267395},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3393487334251404},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3272938132286072},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32557791471481323},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871633","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871633","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 ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1595439448","https://openalex.org/W1678356000","https://openalex.org/W1988217119","https://openalex.org/W2078206655","https://openalex.org/W2102189859","https://openalex.org/W2108223890","https://openalex.org/W2124576009","https://openalex.org/W2140602286","https://openalex.org/W2171743956","https://openalex.org/W6680646450"],"related_works":["https://openalex.org/W4244466418","https://openalex.org/W2104062382","https://openalex.org/W2162878363","https://openalex.org/W2389021890","https://openalex.org/W2479325685","https://openalex.org/W4245101192","https://openalex.org/W2146588098","https://openalex.org/W3183791698","https://openalex.org/W3111710556","https://openalex.org/W2480873127"],"abstract_inverted_index":{"We":[0,55,78],"propose":[1,57],"a":[2,6,58,64,87],"classification":[3,59],"taxonomy":[4,25],"over":[5,86],"large":[7,88],"crawl":[8],"of":[9,66,83,90],"HTML":[10,93],"tables":[11,19,27,74,94],"on":[12,17,80,95],"the":[13,67,81,96],"Web,":[14],"focusing":[15],"primarily":[16],"those":[18,33,44],"that":[20],"express":[21],"structured":[22],"knowledge.":[23],"The":[24],"separates":[26],"into":[28],"two":[29],"top-level":[30],"classes:":[31],"a)":[32],"used":[34],"for":[35,61],"layout":[36,73],"purposes,":[37],"including":[38,48],"navigational":[39],"and":[40,42,53,75],"formatting;":[41],"b)":[43],"containing":[45],"relational":[46],"knowledge,":[47],"listings,":[49],"attribute/value,":[50],"matrix,":[51],"enumeration,":[52],"form.":[54],"then":[56],"algorithm":[60],"automatically":[62],"detecting":[63],"subset":[65],"classes":[68],"in":[69],"our":[70,84],"taxonomy,":[71],"namely":[72],"attribute/value":[76],"tables.":[77],"report":[79],"performance":[82],"system":[85],"sample":[89],"manually":[91],"annotated":[92],"Web.":[97]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
