{"id":"https://openalex.org/W2118224394","doi":"https://doi.org/10.1145/1135777.1135935","title":"Using graph matching techniques to wrap data from PDF documents","display_name":"Using graph matching techniques to wrap data from PDF documents","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2118224394","doi":"https://doi.org/10.1145/1135777.1135935","mag":"2118224394"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135935","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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/A5102797774","display_name":"Tamir Hassan","orcid":"https://orcid.org/0000-0002-1940-1037"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Tamir Hassan","raw_affiliation_strings":["Vienna University of Technology, Wien, Austria","Vienna Univ. of Technology, Wien, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Wien, Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Vienna Univ. of Technology, Wien, Austria#TAB#","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055923468","display_name":"Robert Baumgartner","orcid":"https://orcid.org/0000-0003-0899-4903"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Robert Baumgartner","raw_affiliation_strings":["Vienna University of Technology, Wien, Austria","Vienna Univ. of Technology, Wien, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Wien, Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Vienna Univ. of Technology, Wien, Austria#TAB#","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102797774"],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":2.4625,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.91243155,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"901","last_page":"902"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9993000030517578,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8172382712364197},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.6479250192642212},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5825963020324707},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5318861603736877},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5089588165283203},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48068222403526306},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4500770568847656},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4487636089324951},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27847862243652344},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1628859043121338},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08906364440917969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172382712364197},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6479250192642212},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5825963020324707},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5318861603736877},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5089588165283203},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48068222403526306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4500770568847656},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4487636089324951},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27847862243652344},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1628859043121338},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08906364440917969},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1135777.1135935","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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":3,"referenced_works":["https://openalex.org/W2122306963","https://openalex.org/W2136761100","https://openalex.org/W2148210463"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W4301594054","https://openalex.org/W2794488505","https://openalex.org/W3125889879","https://openalex.org/W3124422538","https://openalex.org/W2295467472","https://openalex.org/W3046451053","https://openalex.org/W2097909533","https://openalex.org/W2144398666","https://openalex.org/W3125188128"],"abstract_inverted_index":{"Wrapping":[0],"is":[1,43,55,71,75],"the":[2,32,59,68,86,106],"process":[3],"of":[4,28,48,62,108],"navigating":[5],"a":[6,16,26,46,76,82,96],"data":[7,11,20,36],"source,":[8],"semi-automatically":[9],"extracting":[10],"and":[12],"transforming":[13],"it":[14],"into":[15,88],"form":[17],"suitable":[18],"for":[19,34],"processing":[21],"applications.":[22],"There":[23],"are":[24,91],"currently":[25],"number":[27],"established":[29],"products":[30],"on":[31,112],"market":[33],"wrapping":[35,60,117],"from":[37],"web":[38],"pages.":[39],"One":[40],"such":[41],"approach":[42],"Lixto":[44,63],"[1],":[45],"product":[47],"research":[49,104],"performed":[50],"at":[51],"our":[52,102],"institute.Our":[53],"work":[54],"concerned":[56],"with":[57],"extending":[58],"functionality":[61],"to":[64,84,115],"PDF":[65,69],"documents.":[66],"As":[67],"format":[70],"relatively":[72],"unstructured,":[73],"this":[74,113],"challenging":[77],"task.":[78],"We":[79],"have":[80],"developed":[81],"method":[83],"segment":[85],"page":[87],"blocks,":[89],"which":[90],"represented":[92],"as":[93],"nodes":[94],"in":[95,105],"relational":[97,109],"graph.":[98],"This":[99],"paper":[100],"describes":[101],"current":[103],"use":[107],"matching":[110],"techniques":[111],"graph":[114],"locate":[116],"instances.":[118]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
