{"id":"https://openalex.org/W2159800521","doi":null,"title":"Making Latin Manuscripts Searchable using gHMM's","display_name":"Making Latin Manuscripts Searchable using gHMM's","publication_year":2004,"publication_date":"2004-12-01","ids":{"openalex":"https://openalex.org/W2159800521","mag":"2159800521"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.111.55","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.55","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips17/NIPS2004_0550.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5021335275","display_name":"Jaety Edwards","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaety Edwards","raw_affiliation_strings":["Department of Computer Science, UC-Berkeley, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, UC-Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064373793","display_name":"Yee Whye Teh","orcid":"https://orcid.org/0000-0001-5365-6933","observed_orcids":["https://orcid.org/0000-0001-5365-6933"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yee Whye Teh","raw_affiliation_strings":["Department of Computer Science, UC-Berkeley, Berkeley, CA"],"raw_orcid":"https://orcid.org/0000-0001-5365-6933","affiliations":[{"raw_affiliation_string":"Department of Computer Science, UC-Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064334986","display_name":"Roger Bock","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roger Bock","raw_affiliation_strings":["Department of Computer Science, UC-Berkeley, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, UC-Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001371942","display_name":"Michael Maire","orcid":"https://orcid.org/0000-0002-9778-6673","observed_orcids":["https://orcid.org/0000-0002-9778-6673"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Maire","raw_affiliation_strings":["Department of Computer Science, UC-Berkeley, Berkeley, CA"],"raw_orcid":"https://orcid.org/0000-0002-9778-6673","affiliations":[{"raw_affiliation_string":"Department of Computer Science, UC-Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074042357","display_name":"Grace Vesom","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace Vesom","raw_affiliation_strings":["Department of Computer Science, UC-Berkeley, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, UC-Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010851725","display_name":"David Alexander Forsyth","orcid":"https://orcid.org/0000-0002-2278-0752","observed_orcids":["https://orcid.org/0000-0002-2278-0752"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Forsyth","raw_affiliation_strings":["Department of Computer Science, UC-Berkeley, Berkeley, CA"],"raw_orcid":"https://orcid.org/0000-0002-2278-0752","affiliations":[{"raw_affiliation_string":"Department of Computer Science, UC-Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.7139,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.91276662,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":"17","issue":null,"first_page":"385","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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/T12377","display_name":"Digital Humanities and Scholarship","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":9.999999747378752e-05,"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/full-text-retrieval","display_name":"full-text search","score":0.5730000138282776},{"id":"https://openalex.org/keywords/generalized-hidden-markov-models","display_name":"generalized hidden Markov models","score":0.8820000290870667},{"id":"https://openalex.org/keywords/medieval-manuscripts","display_name":"medieval manuscripts","score":0.5339999794960022},{"id":"https://openalex.org/keywords/terence","display_name":"Terence","score":0.8600000143051147},{"id":"https://openalex.org/keywords/spelling-variants","display_name":"spelling variants","score":0.6959999799728394}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9681988954544067},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.9432471990585327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142505645751953},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5798318982124329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5702602863311768},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5069530010223389},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4708611071109772},{"id":"https://openalex.org/C20228898","wikidata":"https://www.wikidata.org/wiki/Q83540","display_name":"Full text search","level":3,"score":0.4198858141899109},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3964279890060425},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3963882625102997},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2692466080188751}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.111.55","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.55","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips17/NIPS2004_0550.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.93.4180","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.93.4180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~mmaire/papers/latin_nips2004.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:150526","doi":null,"is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/150526/","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,"listed_in":[],"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. 385-392). (2004)","raw_type":"Proceedings paper"},{"id":"mag:2159800521","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/2706-making-latin-manuscripts-searchable-using-ghmms.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2057175746","https://openalex.org/W2112796928","https://openalex.org/W2138247936","https://openalex.org/W2142069714","https://openalex.org/W2147220807","https://openalex.org/W2156301828","https://openalex.org/W2168868236"],"related_works":["https://openalex.org/W2167929403","https://openalex.org/W2049105599","https://openalex.org/W2886729879","https://openalex.org/W6921559595","https://openalex.org/W4410761886","https://openalex.org/W7117173582","https://openalex.org/W7018479529","https://openalex.org/W7097029480","https://openalex.org/W7140095545","https://openalex.org/W4307356327"],"abstract_inverted_index":{"We":[0,43],"describe":[1],"a":[2,7,28,58,100],"method":[3,53],"that":[4,84],"can":[5],"make":[6],"scanned,":[8],"handwritten":[9,117],"mediaeval":[10],"latin":[11,25],"manuscript":[12,59],"accessible":[13],"to":[14,26,38,82,135],"full":[15],"text":[16],"search.":[17],"A":[18],"generalized":[19],"HMM":[20],"is":[21,123],"fitted,":[22],"using":[23],"transcribed":[24],"obtain":[27,39],"transition":[29],"model":[30,95],"and":[31,49,120],"one":[32],"example":[33],"each":[34],"of":[35,57,60,67,79,90,116,132,137,139,148],"22":[36],"letters":[37,68],"an":[40],"emission":[41],"model.":[42],"show":[44],"results":[45,72],"for":[46],"unigram,":[47],"bigram":[48],"trigram":[50],"models.":[51],"Our":[52],"transcribes":[54],"25":[55],"pages":[56,138],"Terence":[61],"with":[62],"fair":[63,97],"accuracy":[64],"(75":[65],"%":[66],"correctly":[69],"transcribed).":[70],"Search":[71],"are":[73,112],"very":[74],"strong;":[75],"we":[76,104],"use":[77],"examples":[78],"variant":[80],"spellings":[81],"demonstrate":[83],"the":[85,88,91,129],"search":[86],"respects":[87],"ink":[89],"document.":[92],"Furthermore,":[93],"our":[94],"produces":[96],"searches":[98],"on":[99],"document":[101],"from":[102,128],"which":[103],"obtained":[105],"no":[106],"training":[107],"data.":[108],"1.":[109],"Intoduction":[110],"There":[111],"many":[113],"large":[114],"corpora":[115,150],"scanned":[118],"documents,":[119],"their":[121],"number":[122],"growing":[124],"rapidly.":[125],"Collections":[126],"range":[127],"complete":[130],"works":[131],"Mark":[133],"Twain":[134],"thousands":[136],"zoological":[140],"notes":[141],"spanning":[142],"two":[143],"centuries.":[144],"Large":[145],"scale":[146],"analyses":[147],"such":[149]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}
