{"id":"https://openalex.org/W2294936362","doi":"https://doi.org/10.3115/v1/n15-1032","title":"Digital Leafleting: Extracting Structured Data from Multimedia Online Flyers","display_name":"Digital Leafleting: Extracting Structured Data from Multimedia Online Flyers","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2294936362","doi":"https://doi.org/10.3115/v1/n15-1032","mag":"2294936362"},"language":"en","primary_location":{"id":"doi:10.3115/v1/n15-1032","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/n15-1032","pdf_url":"https://www.aclweb.org/anthology/N15-1032.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/N15-1032.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046655683","display_name":"Emilia Apostolova","orcid":"https://orcid.org/0000-0003-2081-4530"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Emilia Apostolova","raw_affiliation_strings":["BrokerSavant Inc. 2506 N. Clark St, 415 Chicago, IL 60614, USA"],"affiliations":[{"raw_affiliation_string":"BrokerSavant Inc. 2506 N. Clark St, 415 Chicago, IL 60614, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053523229","display_name":"Payam Pourashraf","orcid":null},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Payam Pourashraf","raw_affiliation_strings":["DePaul University 243 S Wabash Ave Chicago, IL 60604, USA"],"affiliations":[{"raw_affiliation_string":"DePaul University 243 S Wabash Ave Chicago, IL 60604, USA","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073099618","display_name":"Jeffrey D. Sack","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeffrey Sack","raw_affiliation_strings":["BrokerSavant Inc. 2506 N. Clark St, 415 Chicago, IL 60614, USA"],"affiliations":[{"raw_affiliation_string":"BrokerSavant Inc. 2506 N. Clark St, 415 Chicago, IL 60614, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046655683"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7946,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82866361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"283","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8301008939743042},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7355138063430786},{"id":"https://openalex.org/keywords/infographic","display_name":"Infographic","score":0.6542888283729553},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6145607233047485},{"id":"https://openalex.org/keywords/real-estate","display_name":"Real estate","score":0.6038179993629456},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.47416961193084717},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4271194636821747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39396369457244873},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3673977255821228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3283352851867676},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20697370171546936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301008939743042},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7355138063430786},{"id":"https://openalex.org/C156365220","wikidata":"https://www.wikidata.org/wiki/Q845734","display_name":"Infographic","level":2,"score":0.6542888283729553},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6145607233047485},{"id":"https://openalex.org/C82279013","wikidata":"https://www.wikidata.org/wiki/Q684740","display_name":"Real estate","level":2,"score":0.6038179993629456},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.47416961193084717},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4271194636821747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39396369457244873},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3673977255821228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3283352851867676},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20697370171546936},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/n15-1032","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/n15-1032","pdf_url":"https://www.aclweb.org/anthology/N15-1032.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/n15-1032","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/n15-1032","pdf_url":"https://www.aclweb.org/anthology/N15-1032.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2294936362.pdf","grobid_xml":"https://content.openalex.org/works/W2294936362.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W167522204","https://openalex.org/W1510772064","https://openalex.org/W1524517437","https://openalex.org/W1553019137","https://openalex.org/W1559743959","https://openalex.org/W1566513354","https://openalex.org/W1593502373","https://openalex.org/W1911763874","https://openalex.org/W1967350923","https://openalex.org/W1970243205","https://openalex.org/W1978394996","https://openalex.org/W1983073929","https://openalex.org/W1999643056","https://openalex.org/W2005422315","https://openalex.org/W2005646337","https://openalex.org/W2020278455","https://openalex.org/W2063287522","https://openalex.org/W2072326204","https://openalex.org/W2094400120","https://openalex.org/W2095680579","https://openalex.org/W2105948726","https://openalex.org/W2118020653","https://openalex.org/W2135479443","https://openalex.org/W2140321362","https://openalex.org/W2149684865","https://openalex.org/W2153635508","https://openalex.org/W2154159734","https://openalex.org/W2156909104","https://openalex.org/W2164565864","https://openalex.org/W2435251607","https://openalex.org/W2503755628","https://openalex.org/W3022937510","https://openalex.org/W3120421331","https://openalex.org/W3149033012","https://openalex.org/W4230674625","https://openalex.org/W4231009905","https://openalex.org/W4235486249","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2783937668","https://openalex.org/W4389433970","https://openalex.org/W2523628251","https://openalex.org/W2985775149","https://openalex.org/W3021287274","https://openalex.org/W2996895802","https://openalex.org/W4389434054","https://openalex.org/W3160274551","https://openalex.org/W2799836731","https://openalex.org/W1977852414"],"abstract_inverted_index":{"Marketing":[0],"materials":[1],"such":[2,18,144],"as":[3,19,82,145],"flyers":[4,72,111],"and":[5,75,85,91,112,129,147,157,165,189,200],"other":[6],"infographics":[7],"are":[8,26,132],"a":[9,14,44,61,93,153],"vast":[10],"online":[11],"resource.":[12],"In":[13,56],"number":[15],"of":[16,33,47,53,104,155,173],"industries,":[17],"the":[20,29,80,169,197],"commercial":[21,39,69,108],"real":[22,40,70,109],"estate":[23,41,71,110],"industry,":[24],"they":[25],"in":[27,73,140,183],"fact":[28],"only":[30],"authoritative":[31],"source":[32],"information.":[34,55,174],"Companies":[35],"attempting":[36],"to":[37,121,185],"organize":[38],"inventories":[42],"spend":[43],"significant":[45],"amount":[46],"resources":[48],"on":[49,134,180],"manual":[50],"data":[51,66],"entry":[52],"this":[54,57],"work,":[58],"we":[59],"propose":[60],"method":[62],"for":[63,195],"extracting":[64],"structured":[65,116],"from":[67],"free-form":[68],"PDF":[74,146],"HTML":[76,148],"formats.":[77],"We":[78,175],"modeled":[79],"problem":[81],"text":[83,127,187,198],"categorization":[84,128,199],"Named":[86],"Entity":[87],"Recognition":[88],"(NER)":[89],"tasks":[90],"applied":[92,176],"supervised":[94],"machine":[95],"learning":[96],"approach":[97],"(Support":[98],"Vector":[99],"Machines).":[100],"Our":[101],"dataset":[102],"consists":[103],"more":[105],"than":[106],"2,200":[107],"associated":[113],"manually":[114],"entered":[115],"data,":[117],"which":[118],"was":[119],"used":[120],"automatically":[122],"create":[123],"training":[124],"datasets.":[125],"Traditionally,":[126],"NER":[130,201],"approaches":[131],"based":[133,179],"textual":[135,156],"information":[136,139],"only.":[137],"However,":[138],"visually":[141,162],"rich":[142],"formats":[143],"is":[149],"often":[150,167],"conveyed":[151],"by":[152],"combination":[154],"visual":[158,181],"features.":[159],"Large":[160],"fonts,":[161],"salient":[163],"colors,":[164],"positioning":[166],"indicate":[168],"most":[170],"relevant":[171],"pieces":[172],"novel":[177],"features":[178,188],"characteristics":[182],"addition":[184],"traditional":[186],"show":[190],"that":[191],"performance":[192],"improved":[193],"significantly":[194],"both":[196],"tasks.":[202]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}