{"id":"https://openalex.org/W2134164043","doi":"https://doi.org/10.3115/1034678.1034746","title":"Learning to recognize tables in free text","display_name":"Learning to recognize tables in free text","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W2134164043","doi":"https://doi.org/10.3115/1034678.1034746","mag":"2134164043"},"language":"en","primary_location":{"id":"doi:10.3115/1034678.1034746","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034746","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034746","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034746","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110081955","display_name":"Hwee Tou Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I28490864","display_name":"DSO National Laboratories","ror":"https://ror.org/03e05fb06","country_code":"SG","type":"nonprofit","lineage":["https://openalex.org/I28490864"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hwee Tou Ng","raw_affiliation_strings":["DSO National Laboratories, Singapore","DSO National Laboratories; Singapore"],"affiliations":[{"raw_affiliation_string":"DSO National Laboratories, Singapore","institution_ids":["https://openalex.org/I28490864"]},{"raw_affiliation_string":"DSO National Laboratories; Singapore","institution_ids":["https://openalex.org/I28490864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046448339","display_name":"Chung Yong Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I28490864","display_name":"DSO National Laboratories","ror":"https://ror.org/03e05fb06","country_code":"SG","type":"nonprofit","lineage":["https://openalex.org/I28490864"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chung Yong Lim","raw_affiliation_strings":["DSO National Laboratories, Singapore","DSO National Laboratories; Singapore"],"affiliations":[{"raw_affiliation_string":"DSO National Laboratories, Singapore","institution_ids":["https://openalex.org/I28490864"]},{"raw_affiliation_string":"DSO National Laboratories; Singapore","institution_ids":["https://openalex.org/I28490864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057421552","display_name":"Jessica Li Teng Koo","orcid":null},"institutions":[{"id":"https://openalex.org/I28490864","display_name":"DSO National Laboratories","ror":"https://ror.org/03e05fb06","country_code":"SG","type":"nonprofit","lineage":["https://openalex.org/I28490864"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jessica Li Teng Koo","raw_affiliation_strings":["DSO National Laboratories, Singapore","DSO National Laboratories; Singapore"],"affiliations":[{"raw_affiliation_string":"DSO National Laboratories, Singapore","institution_ids":["https://openalex.org/I28490864"]},{"raw_affiliation_string":"DSO National Laboratories; Singapore","institution_ids":["https://openalex.org/I28490864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110081955"],"corresponding_institution_ids":["https://openalex.org/I28490864"],"apc_list":null,"apc_paid":null,"fwci":3.1851,"has_fulltext":true,"cited_by_count":76,"citation_normalized_percentile":{"value":0.92596083,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"443","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9966999888420105,"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":0.9966999888420105,"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/T10028","display_name":"Topic Modeling","score":0.991599977016449,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.8438276052474976},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792702913284302},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.766434907913208},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5661185383796692},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5537247061729431},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4863601326942444},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4721113443374634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47065913677215576},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46001455187797546},{"id":"https://openalex.org/keywords/decision-table","display_name":"Decision table","score":0.4249327778816223},{"id":"https://openalex.org/keywords/row-and-column-spaces","display_name":"Row and column spaces","score":0.4193892478942871},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28978076577186584},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11879858374595642},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11436012387275696},{"id":"https://openalex.org/keywords/rough-set","display_name":"Rough set","score":0.09428948163986206}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8438276052474976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792702913284302},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.766434907913208},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5661185383796692},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5537247061729431},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4863601326942444},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4721113443374634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47065913677215576},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46001455187797546},{"id":"https://openalex.org/C172967692","wikidata":"https://www.wikidata.org/wiki/Q747762","display_name":"Decision table","level":3,"score":0.4249327778816223},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.4193892478942871},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28978076577186584},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11879858374595642},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11436012387275696},{"id":"https://openalex.org/C111012933","wikidata":"https://www.wikidata.org/wiki/Q3137210","display_name":"Rough set","level":2,"score":0.09428948163986206},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/1034678.1034746","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034746","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034746","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.3910","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.3910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P99/P99-1057.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.30.9484","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.30.9484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dso.org.sg/docs/Freetext.ps","raw_type":"text"},{"id":"pmh:oai:acl.sr.language-archives.org:P99-1057","is_oa":false,"landing_page_url":"http://www.aclweb.org/anthology/P99-1057","pdf_url":null,"source":{"id":"https://openalex.org/S4306402137","display_name":"The COCOON platform (University of Paris)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102197404","host_organization_name":"Universit\u00e9 Paris-Sud","host_organization_lineage":["https://openalex.org/I102197404"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.3115/1034678.1034746","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034746","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034746","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2134164043.pdf","grobid_xml":"https://content.openalex.org/works/W2134164043.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W178986155","https://openalex.org/W652695657","https://openalex.org/W2125055259","https://openalex.org/W2141765212","https://openalex.org/W2766736793"],"related_works":["https://openalex.org/W2313440505","https://openalex.org/W3123744736","https://openalex.org/W2137691148","https://openalex.org/W1505848319","https://openalex.org/W4281971614","https://openalex.org/W2131131934","https://openalex.org/W4226523698","https://openalex.org/W4385281412","https://openalex.org/W2070384782","https://openalex.org/W2352535604"],"abstract_inverted_index":{"Many":[0],"real-world":[1],"texts":[2,10,98],"contain":[3],"tables.":[4,30,54],"In":[5,31],"order":[6],"to":[7,23,41,97],"process":[8],"these":[9],"correctly":[11],"and":[12,27,51,94],"extract":[13],"the":[14,18,25,48],"information":[15],"contained":[16],"within":[17],"tables,":[19],"it":[20],"is":[21,90],"important":[22],"identify":[24],"presence":[26],"structure":[28],"of":[29,53,85],"this":[32],"paper,":[33],"we":[34],"present":[35],"a":[36,67,82],"new":[37],"approach":[38,65,89],"that":[39,72,77],"learns":[40],"recognize":[42],"tables":[43,79],"in":[44,99],"free":[45],"text,":[46],"including":[47],"boundary,":[49],"rows":[50],"columns":[52],"When":[55],"tested":[56],"on":[57,81],"Wall":[58],"Street":[59],"Journal":[60],"news":[61],"documents,":[62],"our":[63],"learning":[64,88],"outperforms":[66],"deterministic":[68],"table":[69,74,104],"recognition":[70,75],"algorithm":[71,76],"identifies":[73,78],"based":[80],"fixed":[83],"set":[84],"conditions.":[86],"Our":[87],"also":[91],"more":[92],"flexible":[93],"easily":[95],"adaptable":[96],"different":[100,103],"domains":[101],"with":[102],"characteristics.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}