{"id":"https://openalex.org/W2005731091","doi":"https://doi.org/10.1145/2513166.2513175","title":"Towards generic framework for tabular data extraction and management in documents","display_name":"Towards generic framework for tabular data extraction and management in documents","publication_year":2013,"publication_date":"2013-10-29","ids":{"openalex":"https://openalex.org/W2005731091","doi":"https://doi.org/10.1145/2513166.2513175","mag":"2005731091"},"language":"en","primary_location":{"id":"doi:10.1145/2513166.2513175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2513166.2513175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth workshop on Ph.D. students in information and knowledge 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/A5021836293","display_name":"Roya Rastan","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Roya Rastan","raw_affiliation_strings":["University of New South Wales, Sydney, Australia","University of New South wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"University of New South wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5021836293"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":2.4268,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90740147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"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":0.9973999857902527,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8319331407546997},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.8273647427558899},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6891444325447083},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6213172078132629},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5761428475379944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5317277908325195},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5237928628921509},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5214985013008118},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5085631608963013},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5003437995910645},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4382493495941162},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4186282157897949},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34106409549713135},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11953100562095642},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09327247738838196},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08644598722457886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319331407546997},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8273647427558899},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6891444325447083},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6213172078132629},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5761428475379944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5317277908325195},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5237928628921509},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5214985013008118},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5085631608963013},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5003437995910645},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4382493495941162},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4186282157897949},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34106409549713135},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11953100562095642},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09327247738838196},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08644598722457886},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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:10.1145/2513166.2513175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2513166.2513175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth workshop on Ph.D. students in information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324887","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W214170106","https://openalex.org/W1506666816","https://openalex.org/W1529144909","https://openalex.org/W1569639771","https://openalex.org/W1593415176","https://openalex.org/W1723485573","https://openalex.org/W1967830139","https://openalex.org/W1969621019","https://openalex.org/W1981453410","https://openalex.org/W1994384332","https://openalex.org/W2001783238","https://openalex.org/W2007713886","https://openalex.org/W2009659675","https://openalex.org/W2022760666","https://openalex.org/W2034797903","https://openalex.org/W2056797079","https://openalex.org/W2102189859","https://openalex.org/W2106170438","https://openalex.org/W2135678693","https://openalex.org/W2136379584","https://openalex.org/W2137435551","https://openalex.org/W2137998699","https://openalex.org/W2139893662","https://openalex.org/W2143694330","https://openalex.org/W2148528790","https://openalex.org/W2150652226","https://openalex.org/W2151825758","https://openalex.org/W2163041183","https://openalex.org/W2169781020","https://openalex.org/W2394374969","https://openalex.org/W2495883511","https://openalex.org/W4229847583","https://openalex.org/W4242680284","https://openalex.org/W6680679778","https://openalex.org/W7015581250"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W2397952901","https://openalex.org/W2029380707","https://openalex.org/W4255934811","https://openalex.org/W2465382974","https://openalex.org/W2010229520","https://openalex.org/W2547528905"],"abstract_inverted_index":{"Tables":[0],"are":[1,113],"one":[2],"of":[3,14,19,81,105,124],"the":[4,12,73,78,110,122,131],"common":[5,39],"data":[6,30],"presentation":[7],"structures":[8],"in":[9,22,121,127],"documents.":[10],"However,":[11],"task":[13],"automatic":[15],"recognition":[16],"and":[17,29,63,83,115],"extraction":[18,54,75,87,118],"tables":[20,33,112],"embedded":[21],"documents":[23],"is":[24,48,119],"still":[25,34],"a":[26,85,94],"significant":[27],"challenge,":[28],"contained":[31],"within":[32],"remains":[35],"under-utilised.":[36],"Although":[37],"some":[38],"steps":[40],"can":[41,57,90],"be":[42,58,91],"defined":[43],"for":[44,52,97],"table":[45,53,74,86,98],"extraction,":[46],"there":[47],"no":[49],"generic":[50],"approach":[51],"tasks":[55],"which":[56,89],"applied":[59],"to":[60],"different":[61],"sources":[62],"provide":[64],"an":[65,103],"end-to-end":[66],"repeatable":[67],"work-flow.":[68],"This":[69],"paper":[70],"looks":[71],"at":[72],"problem":[76],"from":[77],"process":[79],"point":[80],"view":[82],"proposes":[84],"workflow,":[88],"considered":[92,120],"as":[93],"plug-and-play":[95],"architecture":[96],"extraction.":[99],"Also,":[100],"we":[101],"present":[102],"overview":[104],"our":[106],"complete":[107],"system":[108],"where":[109],"extracted":[111],"stored":[114],"managed.":[116],"Table":[117],"context":[123],"financial":[125],"statements":[126],"this":[128],"work,":[129],"but":[130],"methods":[132],"apply":[133],"generally.":[134]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}