{"id":"https://openalex.org/W2142290346","doi":"https://doi.org/10.1145/1141753.1141827","title":"Tagging of name records for genealogical data browsing","display_name":"Tagging of name records for genealogical data browsing","publication_year":2006,"publication_date":"2006-06-11","ids":{"openalex":"https://openalex.org/W2142290346","doi":"https://doi.org/10.1145/1141753.1141827","mag":"2142290346"},"language":"en","primary_location":{"id":"doi:10.1145/1141753.1141827","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","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/A5030444995","display_name":"Mike Perrow","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mike Perrow","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101763101","display_name":"David Barber","orcid":"https://orcid.org/0000-0003-2163-2982"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"David Barber","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.8488,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8778012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T11719","display_name":"Data Quality and Management","score":0.9973000288009644,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.7432506084442139},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5727279186248779},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5634098649024963},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4903092682361603},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.4814988374710083},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3849223256111145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30782395601272583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432506084442139},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5727279186248779},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5634098649024963},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4903092682361603},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.4814988374710083},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3849223256111145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30782395601272583},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1141753.1141827","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.295.8915","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.295.8915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web4.cs.ucl.ac.uk/staff/D.Barber/publications/perrow-barber-tagging-jcdl06.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:83522","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/83522/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:    (pp. pp. 316-325).   (2006)     ","raw_type":"Proceedings paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320331353","display_name":"National Center of Competence in Research Chemical Biology","ror":"https://ror.org/033f9yy33"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W36024057","https://openalex.org/W1520377376","https://openalex.org/W1567355195","https://openalex.org/W1579838312","https://openalex.org/W1610496399","https://openalex.org/W1991133427","https://openalex.org/W2029873015","https://openalex.org/W2049633694","https://openalex.org/W2056826404","https://openalex.org/W2073268792","https://openalex.org/W2081687495","https://openalex.org/W2086699924","https://openalex.org/W2100796029","https://openalex.org/W2125838338","https://openalex.org/W2135843243","https://openalex.org/W2137939096","https://openalex.org/W2143683307","https://openalex.org/W2159080219","https://openalex.org/W2162337786","https://openalex.org/W2165741325","https://openalex.org/W2913519381","https://openalex.org/W4256238177"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2502722637","https://openalex.org/W1564661574","https://openalex.org/W1840287803","https://openalex.org/W2384808441","https://openalex.org/W2364838364","https://openalex.org/W2020749411","https://openalex.org/W2144190808","https://openalex.org/W1509467138","https://openalex.org/W2128719260"],"abstract_inverted_index":{"In":[0],"this":[1,107,174,196],"paper":[2],"we":[3,21,109,215,223],"present":[4,170,216],"a":[5,14,27,44,66,70,85,93,97,102,115,180,199,204,217,221],"method":[6],"of":[7,26,46,60,63,69,139,160,167,220],"parsing":[8],"unstructured":[9],"textual":[10],"records":[11,34,83],"briefly":[12],"describing":[13],"person":[15],"and":[16,79,124,137,163,207,231],"their":[17],"direct":[18],"relatives,":[19],"which":[20,87,155],"use":[22],"in":[23,81,211],"the":[24,51,90,125,135,184,190,233],"construction":[25],"browsing":[28],"tool":[29,222],"for":[30,118,134,141],"genealogical":[31,228],"data.":[32,234],"The":[33,56],"have":[35],"been":[36],"created":[37],"by":[38,197],"researchers":[39,229],"who":[40],"are":[41,110,224],"currently":[42],"digitising":[43],"collection":[45],"historical":[47],"archives":[48],"stored":[49],"at":[50],"Abbaye":[52],"de":[53],"Saint-Maurice,":[54],"Switzerland.":[55],"string":[57],"'Beatrix,":[58],"daughter":[59],"Johannes":[61],"Trona,":[62],"Saillon'":[64],"is":[65,92],"typical":[67],"example":[68],"record.":[71],"We":[72,129,169,194],"wish":[73],"to":[74,112,148,173,182,226],"annotate":[75,183],"every":[76],"term":[77,91],"(word":[78],"symbol)":[80],"our":[82,151],"with":[84,150,179],"label":[86],"describes":[88],"whether":[89],"name":[94,120,158],"(e.g.":[95,99,104,121],"'Beatrix'),":[96],"place":[98],"'Saillon'),":[100],"or":[101],"relationship":[103],"'daughter').":[105],"Using":[106],"information,":[108],"able":[111],"derive":[113],"both":[114],"canonical":[116],"form":[117],"each":[119],"'Beatrix":[122],"Trona'),":[123],"relationships":[126],"between":[127],"people.":[128],"build":[130],"upon":[131],"work":[132],"developed":[133],"cleaning":[136],"standardization":[138],"names":[140],"record":[142,205],"linkage":[143],"corpora,":[144],"adding":[145],"several":[146],"enhancements":[147],"deal":[149],"more":[152],"difficult":[153],"data,":[154],"contains":[156],"common":[157],"structures":[159],"French,":[161],"Italian":[162],"Latin,":[164],"over":[165],"hundreds":[166],"years.":[168],"an":[171],"approach":[172],"problem":[175],"that":[176],"works":[177],"interactively":[178],"user":[181],"data":[185],"set":[186],"accurately,":[187],"greatly":[188],"reducing":[189],"human":[191],"effort":[192],"required.":[193],"do":[195],"learning":[198],"Hidden":[200],"Markov":[201],"Model":[202],"representing":[203],"structure,":[206],"finding":[208],"structural":[209],"patterns":[210],"new":[212],"records.":[213],"Finally,":[214],"brief":[218],"overview":[219],"developing":[225],"help":[227],"browse":[230],"search":[232]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
