{"id":"https://openalex.org/W4385595405","doi":"https://doi.org/10.1145/3573128.3604901","title":"WEATHERGOV+","display_name":"WEATHERGOV+","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385595405","doi":"https://doi.org/10.1145/3573128.3604901"},"language":"en","primary_location":{"id":"doi:10.1145/3573128.3604901","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3573128.3604901","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 2023","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/A5046469771","display_name":"Amanda Dash","orcid":"https://orcid.org/0000-0001-8654-1593"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amanda Dash","raw_affiliation_strings":["University of Victoria, Victoria, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8654-1593","affiliations":[{"raw_affiliation_string":"University of Victoria, Victoria, British Columbia, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033597391","display_name":"Melissa Cote","orcid":"https://orcid.org/0000-0002-5594-977X"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Melissa Cote","raw_affiliation_strings":["University of Victoria, Victoria, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5594-977X","affiliations":[{"raw_affiliation_string":"University of Victoria, Victoria, British Columbia, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036029722","display_name":"Alexandra Branzan Albu","orcid":"https://orcid.org/0000-0001-8991-0999"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alexandra Branzan Albu","raw_affiliation_strings":["University of Victoria, Victoria, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8991-0999","affiliations":[{"raw_affiliation_string":"University of Victoria, Victoria, British Columbia, Canada","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08108249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9128861427307129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8648806214332581},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7492669224739075},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7266300916671753},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6556433439254761},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47584769129753113},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.4645073115825653},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.44542965292930603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42273712158203125},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37278634309768677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3638148307800293},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15816915035247803}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9128861427307129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8648806214332581},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7492669224739075},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7266300916671753},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6556433439254761},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47584769129753113},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.4645073115825653},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44542965292930603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42273712158203125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37278634309768677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3638148307800293},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15816915035247803},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573128.3604901","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3573128.3604901","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 2023","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":41,"referenced_works":["https://openalex.org/W1568702397","https://openalex.org/W2003170434","https://openalex.org/W2051265407","https://openalex.org/W2058043539","https://openalex.org/W2101105183","https://openalex.org/W2110803977","https://openalex.org/W2116716943","https://openalex.org/W2119874156","https://openalex.org/W2150673968","https://openalex.org/W2604799547","https://openalex.org/W2739046565","https://openalex.org/W2752442988","https://openalex.org/W2901890385","https://openalex.org/W2950397305","https://openalex.org/W2962905474","https://openalex.org/W2963091658","https://openalex.org/W2963314090","https://openalex.org/W2963592583","https://openalex.org/W2963647456","https://openalex.org/W2978036638","https://openalex.org/W3003206728","https://openalex.org/W3003514020","https://openalex.org/W3004127423","https://openalex.org/W3007604991","https://openalex.org/W3098495697","https://openalex.org/W3107064625","https://openalex.org/W3118722740","https://openalex.org/W3166398748","https://openalex.org/W3167404434","https://openalex.org/W3201922353","https://openalex.org/W3202465222","https://openalex.org/W3205155483","https://openalex.org/W3210221975","https://openalex.org/W3217518891","https://openalex.org/W4200195570","https://openalex.org/W4225829029","https://openalex.org/W4246722913","https://openalex.org/W4309735497","https://openalex.org/W4323556845","https://openalex.org/W4385567217","https://openalex.org/W4385572863"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W4388446985","https://openalex.org/W2003578783"],"abstract_inverted_index":{"Tables,":[0],"ubiquitous":[1],"in":[2,46,54,66,89],"data-oriented":[3],"documents":[4],"like":[5],"scientific":[6],"papers":[7],"and":[8,12,33,35,91,118,203,218,231,235],"financial":[9],"statements,":[10],"organize":[11],"convey":[13],"relational":[14],"information.":[15],"Automatic":[16],"table":[17,69,160,173],"recognition":[18,174],"from":[19,38,124,140],"document":[20,47,126],"images,":[21],"which":[22],"involves":[23],"detection":[24],"within":[25],"the":[26,85,103,106,116,141,157,181,184,194,198,204,207,229],"page,":[27],"structural":[28],"segmentation":[29],"into":[30],"rows,":[31],"columns,":[32],"cells,":[34,39],"information":[36],"extraction":[37],"has":[40],"been":[41],"a":[42,99],"popular":[43],"research":[44,216,227],"topic":[45],"image":[48],"analysis":[49],"(DIA).":[50],"With":[51,214],"recent":[52],"advances":[53],"natural":[55],"language":[56],"generation":[57],"(NLG)":[58],"based":[59],"on":[60],"deep":[61],"neural":[62],"networks,":[63],"data-to-text":[64],"generation,":[65],"particular":[67],"for":[68,108,115,176,228],"summarization,":[70],"offers":[71],"interesting":[72],"solutions":[73],"to":[74,83,128,196,224],"time-intensive":[75],"data":[76,110,143],"analysis.":[77],"In":[78],"this":[79,215],"paper,":[80],"we":[81,96,222],"aim":[82],"bridge":[84],"gap":[86],"between":[87],"efforts":[88],"DIA":[90],"NLG":[92],"regarding":[93],"tabular":[94,109,142],"data:":[95],"propose":[97,166],"WEATHERGOV+,":[98],"dataset":[100],"building":[101],"upon":[102],"WEATHERGOV":[104,145],"dataset,":[105],"standard":[107],"summarization":[111,177],"techniques,":[112],"that":[113,149,170],"allows":[114],"training":[117],"testing":[119],"of":[120,137,144,153,162,183,193,200,206,233],"end-to-end":[121,168],"methods":[122,175],"working":[123],"input":[125],"images":[127,136],"generate":[129],"text":[130],"summaries":[131,161],"as":[132,211],"output.":[133],"WEATHERGOV+":[134,189],"contains":[135],"tables":[138],"created":[139],"using":[146],"visual":[147],"variations":[148],"cover":[150],"various":[151],"levels":[152],"difficulty,":[154],"along":[155],"with":[156],"corresponding":[158],"human-generated":[159],"WEATHERGOV.":[163],"We":[164,179],"also":[165],"an":[167],"pipeline":[169,186,195],"compares":[171],"state-of-the-art":[172],"purposes.":[178],"analyse":[180],"results":[182],"proposed":[185],"by":[187],"evaluating":[188],"at":[190],"each":[191],"stage":[192],"identify":[197],"effects":[199],"error":[201],"propagation":[202],"weaknesses":[205],"current":[208],"methods,":[209],"such":[210],"OCR":[212],"errors.":[213],"(dataset":[217],"code":[219],"available":[220],"here1),":[221],"hope":[223],"encourage":[225],"new":[226],"processing":[230],"management":[232],"inter-":[234],"intra-document":[236],"collections.":[237]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-08-05T00:00:00"}