{"id":"https://openalex.org/W2970507142","doi":"https://doi.org/10.1145/3328519.3329131","title":"A Collaborative Framework for Structure Identification over Print Documents","display_name":"A Collaborative Framework for Structure Identification over Print Documents","publication_year":2019,"publication_date":"2019-07-05","ids":{"openalex":"https://openalex.org/W2970507142","doi":"https://doi.org/10.1145/3328519.3329131","mag":"2970507142"},"language":"en","primary_location":{"id":"doi:10.1145/3328519.3329131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3328519.3329131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Human-In-the-Loop Data Analytics","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/A5085409429","display_name":"Maeda F. Hanafi","orcid":"https://orcid.org/0009-0005-6663-2320"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Maeda F. Hanafi","raw_affiliation_strings":["NYU Abu Dhabi"],"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075026385","display_name":"Miro Mannino","orcid":"https://orcid.org/0000-0001-7738-1815"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Miro Mannino","raw_affiliation_strings":["NYU Abu Dhabi"],"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044418740","display_name":"Azza Abouzied","orcid":"https://orcid.org/0000-0003-4273-2536"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Azza Abouzied","raw_affiliation_strings":["NYU Abu Dhabi"],"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi","institution_ids":["https://openalex.org/I120250893"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085409429"],"corresponding_institution_ids":["https://openalex.org/I120250893"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13628049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11719","display_name":"Data Quality and Management","score":0.9817000031471252,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.8921849727630615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8665275573730469},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.7587952613830566},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6880630850791931},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.592802882194519},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5355140566825867},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.48484575748443604},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.47141170501708984},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.43704715371131897},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4324687719345093},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.42315956950187683},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3349250257015228},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33060628175735474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25771620869636536}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8921849727630615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665275573730469},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.7587952613830566},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6880630850791931},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.592802882194519},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5355140566825867},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.48484575748443604},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.47141170501708984},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.43704715371131897},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4324687719345093},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.42315956950187683},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3349250257015228},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33060628175735474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25771620869636536},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3328519.3329131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3328519.3329131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Human-In-the-Loop Data Analytics","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":31,"referenced_works":["https://openalex.org/W99136341","https://openalex.org/W790941020","https://openalex.org/W1691409177","https://openalex.org/W1966269264","https://openalex.org/W1981453410","https://openalex.org/W1984130280","https://openalex.org/W2005646337","https://openalex.org/W2034797903","https://openalex.org/W2046797334","https://openalex.org/W2048282669","https://openalex.org/W2060507674","https://openalex.org/W2064766209","https://openalex.org/W2079525773","https://openalex.org/W2098720114","https://openalex.org/W2110412794","https://openalex.org/W2115927545","https://openalex.org/W2125235681","https://openalex.org/W2144951274","https://openalex.org/W2145657314","https://openalex.org/W2158619747","https://openalex.org/W2251812060","https://openalex.org/W2416987009","https://openalex.org/W2577020101","https://openalex.org/W2604259521","https://openalex.org/W2611907972","https://openalex.org/W2769041395","https://openalex.org/W2786480153","https://openalex.org/W2940666954","https://openalex.org/W2959716049","https://openalex.org/W3142730727","https://openalex.org/W4256244129"],"related_works":["https://openalex.org/W2047973478","https://openalex.org/W2032182853","https://openalex.org/W2004087619","https://openalex.org/W4205150741","https://openalex.org/W4321472216","https://openalex.org/W2557094866","https://openalex.org/W2469016277","https://openalex.org/W2362196274","https://openalex.org/W2757101400","https://openalex.org/W1982302668"],"abstract_inverted_index":{"We":[0,93],"describe":[1],"Texture,":[2],"a":[3,89,98],"framework":[4],"for":[5],"data":[6,16,73],"extraction":[7,17],"over":[8,19],"print":[9,42],"documents":[10],"that":[11,36,95],"allows":[12],"end-users":[13,53],"to":[14,32,47,54,60,64],"construct":[15],"rules":[18],"an":[20],"inferred":[21],"document":[22,115],"structure.":[23],"To":[24],"effectively":[25],"infer":[26],"this":[27],"structure,":[28],"we":[29,103],"enable":[30],"developers":[31],"contribute":[33],"multiple":[34],"heuristics":[35,59],"identify":[37],"different":[38,85,114],"structures":[39,112],"in":[40],"English":[41],"documents,":[43],"crowd-workers":[44,76],"and":[45,52,56,62,77,108],"annotators":[46],"manually":[48],"label":[49],"these":[50,84],"structures,":[51],"search":[55],"decide":[57],"which":[58],"apply":[61],"how":[63],"boost":[65],"their":[66],"performance":[67],"with":[68,97],"the":[69],"help":[70],"of":[71,83,91,100],"ground-truth":[72],"collected":[74],"from":[75],"annotators.":[78],"Texture's":[79],"design":[80],"supports":[81],"each":[82],"user":[86],"groups":[87],"through":[88],"suite":[90],"tools.":[92],"demonstrate":[94],"even":[96],"handful":[99],"student-developed":[101],"heuristics,":[102],"can":[104],"achieve":[105],"reasonable":[106],"precision":[107],"recall":[109],"when":[110],"identifying":[111],"across":[113],"collections.":[116]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
