{"id":"https://openalex.org/W4313492076","doi":"https://doi.org/10.1145/3570991.3571037","title":"BUDDI Table Factory: A toolbox for generating synthetic documents with annotated tables and cells","display_name":"BUDDI Table Factory: A toolbox for generating synthetic documents with annotated tables and cells","publication_year":2023,"publication_date":"2023-01-04","ids":{"openalex":"https://openalex.org/W4313492076","doi":"https://doi.org/10.1145/3570991.3571037"},"language":"en","primary_location":{"id":"doi:10.1145/3570991.3571037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD)","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/A5008771617","display_name":"Bharath Sripathy","orcid":"https://orcid.org/0000-0002-3094-7954"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bharath Sripathy","raw_affiliation_strings":["BUDDI AI, India"],"affiliations":[{"raw_affiliation_string":"BUDDI AI, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017364146","display_name":"Harinath Krishnamoorthy","orcid":"https://orcid.org/0000-0002-9095-6529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harinath Krishnamoorthy","raw_affiliation_strings":["BUDDI AI, India"],"affiliations":[{"raw_affiliation_string":"BUDDI AI, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012400928","display_name":"Sudarsun Santhiappan","orcid":"https://orcid.org/0000-0001-5769-2405"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sudarsun Santhiappan","raw_affiliation_strings":["BUDDI AI, India"],"affiliations":[{"raw_affiliation_string":"BUDDI AI, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008771617"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00243893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"218","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9907000064849854,"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"}},{"id":"https://openalex.org/T14319","display_name":"Currency Recognition and Detection","score":0.9785000085830688,"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":0.8551926612854004},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.8007364273071289},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6133772134780884},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.6073381900787354},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.594938337802887},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.489795446395874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43153107166290283},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3800109028816223},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3437635004520416},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08053401112556458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8551926612854004},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8007364273071289},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6133772134780884},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.6073381900787354},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.594938337802887},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.489795446395874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43153107166290283},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3800109028816223},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3437635004520416},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08053401112556458},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3570991.3571037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2037227137","https://openalex.org/W2051265407","https://openalex.org/W2771490691","https://openalex.org/W2786162033","https://openalex.org/W2795424778","https://openalex.org/W2981630388","https://openalex.org/W3003448409","https://openalex.org/W3003496674","https://openalex.org/W3004124585","https://openalex.org/W3101577715","https://openalex.org/W3104049173","https://openalex.org/W3107064625","https://openalex.org/W3122808376","https://openalex.org/W3163021734","https://openalex.org/W3195022506","https://openalex.org/W3201833923","https://openalex.org/W3204079904","https://openalex.org/W3212008804","https://openalex.org/W4285594485","https://openalex.org/W4287084699","https://openalex.org/W4287163563","https://openalex.org/W4297826882","https://openalex.org/W4394831872"],"related_works":["https://openalex.org/W4205140848","https://openalex.org/W2068663075","https://openalex.org/W2978678743","https://openalex.org/W2797837731","https://openalex.org/W4393677513","https://openalex.org/W4390832911","https://openalex.org/W829257147","https://openalex.org/W4385302116","https://openalex.org/W3081389670","https://openalex.org/W2000674637"],"abstract_inverted_index":{"Tables":[0],"are":[1,56],"the":[2,14,28,47,137,149,156,162],"most":[3],"convenient":[4],"way":[5],"to":[6,19,52,98,119,148],"represent":[7],"structured":[8],"information":[9],"in":[10,34,68,90,129,167],"a":[11,85,95,100,115],"document.":[12],"Understanding":[13],"table":[15,36,69,91,103,121,163],"structure":[16,164],"is":[17],"critical":[18],"understanding":[20,35],"its":[21],"contents.":[22],"Several":[23],"deep":[24],"learning-based":[25],"approaches":[26],"from":[27,66,105],"literature":[29],"have":[30],"shown":[31],"promising":[32],"results":[33],"structures,":[37],"but":[38],"they":[39],"require":[40],"large":[41],"amounts":[42],"of":[43,49,88,102,139,161],"annotated":[44,50,82],"data.":[45],"However,":[46],"availability":[48],"datasets":[51],"train":[53],"these":[54],"methods":[55],"expensive,":[57],"laborious,":[58],"and":[59,70,122,125,158,169],"very":[60],"limited.":[61],"Moreover,":[62],"human-annotated":[63],"data":[64],"suffers":[65],"inconsistencies":[67],"cell":[71,123],"annotations.":[72],"We":[73,93,113,134],"propose":[74,94,114],"BUDDI":[75],"Table":[76],"Factory":[77],"(BTF)":[78],"for":[79],"synthetically":[80],"generating":[81],"documents":[83,110,143,147],"with":[84,144],"wide":[86],"range":[87],"variations":[89],"structures.":[92],"heuristics-based":[96],"method":[97],"generate":[99,108,127],"variety":[101],"structures":[104],"which":[106,152],"we":[107],"synthetic":[109,141],"using":[111],"LaTeX.":[112],"computer":[116],"vision-based":[117],"approach":[118],"localize":[120],"regions":[124],"automatically":[126],"annotations":[128],"PASCAL":[130],"VOC":[131],"challenge":[132],"format.":[133],"empirically":[135],"illustrate":[136],"advantage":[138],"adding":[140],"BTF":[142],"limited":[145],"original":[146],"model":[150],"training,":[151],"can":[153],"significantly":[154],"improve":[155],"TEDS":[157],"IoU":[159],"performance":[160],"recognition":[165],"tasks":[166],"public":[168],"real-world":[170],"healthcare":[171],"datasets.":[172]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}