{"id":"https://openalex.org/W3088711103","doi":"https://doi.org/10.1145/3395027.3419580","title":"PDF2LaTeX","display_name":"PDF2LaTeX","publication_year":2020,"publication_date":"2020-09-23","ids":{"openalex":"https://openalex.org/W3088711103","doi":"https://doi.org/10.1145/3395027.3419580","mag":"3088711103"},"language":"en","primary_location":{"id":"doi:10.1145/3395027.3419580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395027.3419580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2020","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/A5085372617","display_name":"Zelun Wang","orcid":"https://orcid.org/0000-0001-6513-2176"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zelun Wang","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024732465","display_name":"Jyh\u2010Charn Liu","orcid":"https://orcid.org/0000-0003-1330-5092"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyh-Charn Liu","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":1.6855,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82958199,"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9965000152587891,"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":0.9312999844551086,"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":0.7664297223091125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5132486820220947},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5121097564697266},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5071563720703125},{"id":"https://openalex.org/keywords/plaintext","display_name":"Plaintext","score":0.4399907886981964},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.426277756690979},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.42526838183403015},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.41082578897476196},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4102594256401062},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33762848377227783},{"id":"https://openalex.org/keywords/encryption","display_name":"Encryption","score":0.2507595717906952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664297223091125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5132486820220947},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5121097564697266},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5071563720703125},{"id":"https://openalex.org/C92717368","wikidata":"https://www.wikidata.org/wiki/Q1162538","display_name":"Plaintext","level":3,"score":0.4399907886981964},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.426277756690979},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.42526838183403015},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.41082578897476196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4102594256401062},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33762848377227783},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.2507595717906952},{"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:10.1145/3395027.3419580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395027.3419580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W139731185","https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W1965976114","https://openalex.org/W1976829395","https://openalex.org/W2001642682","https://openalex.org/W2011296149","https://openalex.org/W2031071334","https://openalex.org/W2037859435","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2144499799","https://openalex.org/W2155027007","https://openalex.org/W2163605009","https://openalex.org/W2168851449","https://openalex.org/W2188635677","https://openalex.org/W2194187530","https://openalex.org/W2521665229","https://openalex.org/W2573021775","https://openalex.org/W2577020101","https://openalex.org/W2626873800","https://openalex.org/W2752903006","https://openalex.org/W2786162033","https://openalex.org/W2787371088","https://openalex.org/W2899771611","https://openalex.org/W2963311793","https://openalex.org/W2963403868","https://openalex.org/W3003334191","https://openalex.org/W3102427165","https://openalex.org/W3208345164","https://openalex.org/W4251989754"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W2111726165","https://openalex.org/W2347460059","https://openalex.org/W2045514505","https://openalex.org/W2078296418","https://openalex.org/W4296345609"],"abstract_inverted_index":{"The":[0,76,189],"mathematical":[1],"contents":[2],"of":[3,78,88,151,168],"scientific":[4],"publications":[5,174],"in":[6,37],"PDF":[7,15,42,58,170],"format":[8],"cannot":[9],"be":[10],"easily":[11],"analyzed":[12],"by":[13,125,204],"regular":[14],"parsers":[16],"and":[17,35,40,44,64,81,128,154,177,183,213],"OCR":[18,27],"tools.":[19],"In":[20,131],"this":[21],"paper,":[22],"we":[23,162],"propose":[24],"a":[25,51,57,86,95,101,116,142,164,198],"novel":[26],"system":[28,135,196],"called":[29],"PDF2LaTeX,":[30],"which":[31],"extracts":[32],"math":[33,79,106,152],"expressions":[34,80,153],"text":[36,82],"both":[38],"postscript":[39],"image-based":[41],"files":[43],"translates":[45],"them":[46],"into":[47,60,156],"LaTeX":[48,158,212],"markup.":[49],"As":[50],"preprocessing":[52],"step,":[53],"PDF2LaTeX":[54,182],"first":[55],"renders":[56],"file":[59],"its":[61],"image":[62,107,149],"format,":[63],"then":[65],"uses":[66,94,115,136],"projection":[67],"profile":[68],"cutting":[69],"(PPC)":[70],"to":[71,104,121,147],"analyze":[72],"the":[73,132,134,157,179,184,194,205,210,214],"page":[74],"layout.":[75],"analysis":[77],"is":[83],"based":[84,109,140],"on":[85,110,141,175],"series":[87],"deep":[89],"learning":[90],"algorithms.":[91],"First,":[92],"it":[93,114],"convolutional":[96],"neural":[97,144],"network":[98,145],"(CNN)":[99],"as":[100],"binary":[102],"classifier":[103],"detect":[105,122],"blocks":[108,150],"visual":[111],"features.":[112],"Next,":[113],"conditional":[117],"random":[118],"field":[119],"(CRF)":[120],"math-text":[123],"boundaries":[124],"incorporating":[126],"semantics":[127],"context":[129],"information.":[130],"end,":[133],"two":[137],"different":[138],"models":[139],"CNN-LSTM":[143],"architecture":[146],"translate":[148],"plaintext":[155],"representations.":[159],"For":[160],"testing,":[161],"created":[163],"new":[165],"dataset":[166],"composed":[167],"102":[169],"pages":[171],"collected":[172],"from":[173],"arXiv.org":[176],"compared":[178],"performance":[180],"between":[181,209],"state-of-the-art":[185],"commercial":[186],"software":[187],"InftyReader.":[188],"experiment":[190],"results":[191],"showed":[192],"that":[193],"proposed":[195],"achieved":[197],"better":[199],"recognition":[200],"accuracy":[201],"(81.1%)":[202],"measured":[203],"string":[206],"edit":[207],"distance":[208],"predicted":[211],"ground":[215],"truth.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-10-01T00:00:00"}