{"id":"https://openalex.org/W4307647392","doi":"https://doi.org/10.1007/s10032-022-00420-9","title":"Tables to LaTeX: structure and content extraction from scientific tables","display_name":"Tables to LaTeX: structure and content extraction from scientific tables","publication_year":2022,"publication_date":"2022-10-27","ids":{"openalex":"https://openalex.org/W4307647392","doi":"https://doi.org/10.1007/s10032-022-00420-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-022-00420-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-022-00420-9","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10032-022-00420-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104083222","display_name":"Pratik Kayal","orcid":null},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Pratik Kayal","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051941533","display_name":"Mrinal Anand","orcid":null},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mrinal Anand","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034426573","display_name":"Harsh Desai","orcid":"https://orcid.org/0000-0002-8540-712X"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harsh Desai","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100746900","display_name":"Mayank Singh","orcid":"https://orcid.org/0000-0001-8757-2623"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mayank Singh","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, India","institution_ids":["https://openalex.org/I27674431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104083222"],"corresponding_institution_ids":["https://openalex.org/I27674431"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.2023,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81665631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"26","issue":"2","first_page":"121","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9955000281333923,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.840649425983429},{"id":"https://openalex.org/keywords/alphanumeric","display_name":"Alphanumeric","score":0.7306557893753052},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6295315027236938},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.5158988237380981},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4849708080291748},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.47671622037887573},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4563260078430176},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.44187620282173157},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4408484101295471},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.424550861120224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38951411843299866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3373069167137146},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33678996562957764},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3129445016384125},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15145832300186157},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14367324113845825},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08685725927352905},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07893726229667664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840649425983429},{"id":"https://openalex.org/C2781003394","wikidata":"https://www.wikidata.org/wiki/Q737372","display_name":"Alphanumeric","level":2,"score":0.7306557893753052},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6295315027236938},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.5158988237380981},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4849708080291748},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.47671622037887573},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4563260078430176},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.44187620282173157},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4408484101295471},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.424550861120224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38951411843299866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3373069167137146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33678996562957764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3129445016384125},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15145832300186157},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14367324113845825},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08685725927352905},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07893726229667664},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.1007/s10032-022-00420-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-022-00420-9","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2210.17246","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.17246","pdf_url":"https://arxiv.org/pdf/2210.17246","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s10032-022-00420-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-022-00420-9","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[{"id":"https://openalex.org/G5081997446","display_name":null,"funder_award_id":"ECR/2018/000087","funder_id":"https://openalex.org/F4320334771","funder_display_name":"Science and Engineering Research Board"}],"funders":[{"id":"https://openalex.org/F4320334771","display_name":"Science and Engineering Research Board","ror":"https://ror.org/03ffdsr55"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W178986155","https://openalex.org/W188433705","https://openalex.org/W1647671624","https://openalex.org/W2001642682","https://openalex.org/W2009659675","https://openalex.org/W2022351003","https://openalex.org/W2136379584","https://openalex.org/W2150673968","https://openalex.org/W2165382068","https://openalex.org/W2194775991","https://openalex.org/W2730951118","https://openalex.org/W2786162033","https://openalex.org/W2795424778","https://openalex.org/W2910896634","https://openalex.org/W2913389685","https://openalex.org/W2963212250","https://openalex.org/W2986670728","https://openalex.org/W3003496674","https://openalex.org/W3003514020","https://openalex.org/W3003711898","https://openalex.org/W3003931580","https://openalex.org/W3004042913","https://openalex.org/W3104049173","https://openalex.org/W3107064625","https://openalex.org/W3109870706","https://openalex.org/W3167404434","https://openalex.org/W4239046149","https://openalex.org/W6601215536","https://openalex.org/W6604972893","https://openalex.org/W6969259846"],"related_works":["https://openalex.org/W2049379968","https://openalex.org/W2461009308","https://openalex.org/W2048515600","https://openalex.org/W2322679734","https://openalex.org/W2507454043","https://openalex.org/W2236176244","https://openalex.org/W2509420154","https://openalex.org/W1979637215","https://openalex.org/W1992508337","https://openalex.org/W2048396828"],"abstract_inverted_index":{"Scientific":[0],"documents":[1,22],"contain":[2],"tables":[3,17],"that":[4,117],"list":[5],"important":[6],"information":[7],"in":[8],"a":[9,24,81],"concise":[10],"fashion.":[11],"Structure":[12],"and":[13,38,44,73,97,105,110,127,135],"content":[14,39,74,111],"extraction":[15],"from":[16],"embedded":[18],"within":[19],"PDF":[20],"research":[21],"is":[23],"very":[25],"challenging":[26],"task":[27],"due":[28],"to":[29,53,84],"the":[30,64,77,93,118,123,129,132],"existence":[31],"of":[32,103,125],"visual":[33],"features":[34,40],"like":[35,41],"spanning":[36],"cells":[37],"mathematical":[42],"symbols":[43],"equations.":[45],"Most":[46],"existing":[47],"table":[48,71,108],"structure":[49,72,109],"identification":[50],"methods":[51],"tend":[52],"ignore":[54],"these":[55],"academic":[56],"writing":[57],"features.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,91],"adapt":[63],"transformer-based":[65],"language":[66],"modeling":[67],"paradigm":[68],"for":[69],"scientific":[70],"extraction.":[75],"Specifically,":[76],"proposed":[78,119],"model":[79],"converts":[80],"tabular":[82],"image":[83],"its":[85],"corresponding":[86],"LaTeX":[87,133],"source":[88],"code.":[89],"Overall,":[90],"outperform":[92],"current":[94],"state-of-the-art":[95],"baselines":[96],"achieve":[98],"an":[99],"exact":[100],"match":[101],"accuracy":[102],"70.35":[104],"49.69%":[106],"on":[107],"extraction,":[112],"respectively.":[113],"Further":[114],"analysis":[115],"demonstrates":[116],"models":[120],"efficiently":[121],"identify":[122],"number":[124],"rows":[126],"columns,":[128],"alphanumeric":[130],"characters,":[131],"tokens,":[134],"symbols.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}