{"id":"https://openalex.org/W2547301599","doi":"https://doi.org/10.1145/2908446.2908473","title":"A Divide-and-Merge Approach for Deep Segmentation of Document Tables","display_name":"A Divide-and-Merge Approach for Deep Segmentation of Document Tables","publication_year":2016,"publication_date":"2016-05-09","ids":{"openalex":"https://openalex.org/W2547301599","doi":"https://doi.org/10.1145/2908446.2908473","mag":"2547301599"},"language":"en","primary_location":{"id":"doi:10.1145/2908446.2908473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2908446.2908473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Informatics and Systems","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/A5006202685","display_name":"Bahadar Ali","orcid":null},"institutions":[{"id":"https://openalex.org/I36001604","display_name":"University of Peshawar","ror":"https://ror.org/02t2qwf81","country_code":"PK","type":"education","lineage":["https://openalex.org/I36001604"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Bahadar Ali","raw_affiliation_strings":["Department of Computer Science, University of Peshawar, Peshawar, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Peshawar, Peshawar, Pakistan","institution_ids":["https://openalex.org/I36001604"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074454844","display_name":"Shah Khusro","orcid":"https://orcid.org/0000-0002-7734-7243"},"institutions":[{"id":"https://openalex.org/I36001604","display_name":"University of Peshawar","ror":"https://ror.org/02t2qwf81","country_code":"PK","type":"education","lineage":["https://openalex.org/I36001604"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Shah Khusro","raw_affiliation_strings":["Department of Computer Science, University of Peshawar, Peshawar, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Peshawar, Peshawar, Pakistan","institution_ids":["https://openalex.org/I36001604"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006202685"],"corresponding_institution_ids":["https://openalex.org/I36001604"],"apc_list":null,"apc_paid":null,"fwci":0.3591,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71333314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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":0.9984999895095825,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9977999925613403,"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":0.9972000122070312,"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":0.8219056129455566},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6719880700111389},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6346040964126587},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5181257128715515},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47043630480766296},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45065945386886597},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.4268905818462372},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36958879232406616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3507394790649414},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20360219478607178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219056129455566},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6719880700111389},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6346040964126587},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5181257128715515},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47043630480766296},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45065945386886597},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.4268905818462372},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36958879232406616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3507394790649414},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20360219478607178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2908446.2908473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2908446.2908473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Informatics and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1151363261","https://openalex.org/W1506666816","https://openalex.org/W2009659675","https://openalex.org/W2026153548","https://openalex.org/W2060507674","https://openalex.org/W2105693220","https://openalex.org/W2106170438","https://openalex.org/W2107092590","https://openalex.org/W2113438614","https://openalex.org/W2132083030","https://openalex.org/W2136379584","https://openalex.org/W2138556038","https://openalex.org/W2139893662","https://openalex.org/W2142218344","https://openalex.org/W2212925590"],"related_works":["https://openalex.org/W1663079876","https://openalex.org/W2069133146","https://openalex.org/W2017545316","https://openalex.org/W2100576949","https://openalex.org/W2159686533","https://openalex.org/W4242339654","https://openalex.org/W2349160795","https://openalex.org/W2100057527","https://openalex.org/W4286681602","https://openalex.org/W3209312100"],"abstract_inverted_index":{"Document":[0],"tables":[1,73,108],"are":[2,42,55,150],"a":[3,22,99,103,154],"rich":[4],"source":[5],"of":[6,33,48,60,72,95,107,125,146],"implicit":[7],"semantics":[8],"hidden":[9],"in":[10,25,122,153],"documents":[11],"which":[12,116,149],"could":[13],"be":[14],"exploited":[15],"for":[16],"better":[17],"searching":[18],"and":[19,35,69,119,138,143,165],"ranking.":[20],"However,":[21,77],"central":[23],"problem":[24],"document":[26],"table":[27,37,46,50,86,96,140],"processing":[28],"systems":[29],"is":[30,109],"the":[31,58,84,92,144],"segmentation":[32,64,101,126],"impure":[34],"incomplete":[36],"segments.":[38],"Many":[39],"existing":[40],"methods":[41,54],"limited":[43,49],"to":[44,90],"basic":[45],"segments":[47],"layout":[51,104,136,155],"complexity.":[52],"These":[53],"passing":[56],"through":[57],"stage":[59],"very":[61],"low":[62],"level":[63],"thus":[65],"missing":[66],"many":[67],"physical":[68],"logical":[70],"structures":[71,79],"producing":[74],"erroneous":[75],"results.":[76],"these":[78],"have":[80],"significant":[81],"impact":[82],"on":[83],"overall":[85],"interpretation.":[87],"In":[88],"order":[89],"gain":[91],"full":[93],"strength":[94],"information":[97],"reusability,":[98],"deep":[100],"with":[102],"independent":[105,156],"representation":[106],"needed.":[110],"This":[111],"paper":[112],"propose":[113],"an":[114],"algorithm":[115,133],"performs":[117],"divide":[118],"merge":[120],"tasks":[121],"different":[123],"phases":[124],"using":[127,162],"matrix":[128],"as":[129],"intermediate":[130],"model.":[131],"The":[132],"covers":[134],"maximum":[135],"complexity":[137],"extracts":[139],"schema,":[141],"data":[142,167],"set":[145],"reading":[147],"paths":[148],"then":[151],"represented":[152],"notation.":[157],"We":[158],"evaluated":[159],"our":[160],"results":[161],"standard":[163],"measures":[164],"open":[166],"sets.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}