{"id":"https://openalex.org/W2043928274","doi":"https://doi.org/10.1109/icdar.2007.4376987","title":"Bibliographic Meta-Data Extraction Using Probabilistic Finite State Transducers","display_name":"Bibliographic Meta-Data Extraction Using Probabilistic Finite State Transducers","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2043928274","doi":"https://doi.org/10.1109/icdar.2007.4376987","mag":"2043928274"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4376987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4376987","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","raw_type":"proceedings-article"},"type":"conference-paper","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/A5112253997","display_name":"Matt Kramer","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. Kramer","raw_affiliation_strings":["German Research Center for Artificial Intelligence, Kaiserslautern, Germany","German Res. Center for Artificial Intelligence, Kaiserslautern"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"German Res. Center for Artificial Intelligence, Kaiserslautern","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079980862","display_name":"Hagen Kaprykowsky","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"H. Kaprykowsky","raw_affiliation_strings":["German Research Center for Artificial Intelligence, Kaiserslautern, Germany","German Res. Center for Artificial Intelligence, Kaiserslautern"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"German Res. Center for Artificial Intelligence, Kaiserslautern","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066294527","display_name":"Daniel Keysers","orcid":"https://orcid.org/0000-0001-8765-475X"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Keysers","raw_affiliation_strings":["German Research Center for Artificial Intelligence, Kaiserslautern, Germany","German Res. Center for Artificial Intelligence, Kaiserslautern"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"German Res. Center for Artificial Intelligence, Kaiserslautern","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088840119","display_name":"Thomas M. Breuel","orcid":null},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"T. Breuel","raw_affiliation_strings":["Technical University of Kaiserslautern, Germany","1German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"1German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"609","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9995999932289124,"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/T10260","display_name":"Software Engineering Research","score":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7755422592163086},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7213588356971741},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6980957388877869},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6883417963981628},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.6298548579216003},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6078973412513733},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.561863362789154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5504294037818909},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4799899756908417},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4440705478191376},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4114798903465271},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.402688205242157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36593741178512573},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12310135364532471},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11160564422607422},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10610193014144897},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08661070466041565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7755422592163086},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7213588356971741},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6980957388877869},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6883417963981628},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.6298548579216003},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6078973412513733},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.561863362789154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5504294037818909},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4799899756908417},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4440705478191376},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4114798903465271},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.402688205242157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36593741178512573},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12310135364532471},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11160564422607422},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10610193014144897},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08661070466041565},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdar.2007.4376987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4376987","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W200335640","https://openalex.org/W1513141203","https://openalex.org/W1534730506","https://openalex.org/W1568339100","https://openalex.org/W1608864735","https://openalex.org/W1829303854","https://openalex.org/W1966498024","https://openalex.org/W1994584977","https://openalex.org/W2017473312","https://openalex.org/W2040713190","https://openalex.org/W2043980304","https://openalex.org/W2087382212","https://openalex.org/W2087626139","https://openalex.org/W2093476618","https://openalex.org/W2107394001","https://openalex.org/W2109757083","https://openalex.org/W2122092249","https://openalex.org/W2124479173","https://openalex.org/W2125529971","https://openalex.org/W2127674618","https://openalex.org/W2140479099","https://openalex.org/W2144564434","https://openalex.org/W2145130412","https://openalex.org/W2147880316","https://openalex.org/W2154498027","https://openalex.org/W2156093156","https://openalex.org/W2163737492","https://openalex.org/W2168190036","https://openalex.org/W4235720003","https://openalex.org/W4252090733","https://openalex.org/W4253723135","https://openalex.org/W6608050333","https://openalex.org/W6631918358","https://openalex.org/W6634115791","https://openalex.org/W6636537247","https://openalex.org/W6678720029","https://openalex.org/W6682082992"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3121791438"],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,10,21,53,98],"application":[3],"of":[4,12,69,73,79],"probabilistic":[5],"finite":[6],"state":[7],"transducers":[8],"to":[9,47,85],"task":[11],"bibliographic":[13],"meta-data":[14],"extraction":[15],"from":[16],"scientific":[17],"references.":[18],"By":[19],"using":[20,102],"transducer":[22],"approach,":[23],"which":[24],"is":[25],"often":[26],"applied":[27],"successfully":[28],"in":[29,41],"computational":[30],"linguistics,":[31],"we":[32,89],"obtain":[33],"a":[34,59,66,83,103],"trainable":[35],"and":[36,44,75,107],"modular":[37],"framework.":[38],"This":[39],"results":[40],"simplicity,":[42],"flexibility,":[43],"easy":[45],"adaptability":[46],"changing":[48],"requirements.":[49],"An":[50],"evaluation":[51],"on":[52,82,97],"Cora":[54],"dataset":[55],"that":[56,91],"serves":[57],"as":[58],"common":[60],"benchmark":[61],"for":[62],"accuracy":[63,68,72,78],"measurements":[64],"yields":[65],"word":[67],"88.5%,":[70],"afield":[71],"82.6%,":[74],"an":[76],"instance":[77],"42.7%.":[80],"Based":[81],"comparison":[84],"other":[86],"published":[87],"results,":[88],"conclude":[90],"our":[92],"system":[93],"performs":[94],"second":[95],"best":[96],"given":[99],"data":[100],"set":[101],"conceptually":[104],"simple":[105],"approach":[106],"implementation.":[108]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}