{"id":"https://openalex.org/W2295528958","doi":null,"title":"Lexicon Discovery for Language Preservation using Unsupervised Word Segmentation with Pitman-Yor Language Models (FGNT-2015-01)","display_name":"Lexicon Discovery for Language Preservation using Unsupervised Word Segmentation with Pitman-Yor Language Models (FGNT-2015-01)","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2295528958","mag":"2295528958"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.703.7460","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.703.7460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nt.uni-paderborn.de/public/pubs/2015/WaHaStHi.pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W2295528958"],"child_works_count":0,"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/A5022949022","display_name":"Oliver Walter","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Walter","raw_affiliation_strings":["Paderborn Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn Univ","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330","observed_orcids":["https://orcid.org/0000-0001-9468-7330"]},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb\u2010Umbach","raw_affiliation_strings":["Paderborn Univ"],"raw_orcid":"https://orcid.org/0000-0001-9468-7330","affiliations":[{"raw_affiliation_string":"Paderborn Univ","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066436233","display_name":"Jan Strunk","orcid":"https://orcid.org/0000-0001-8546-1778","observed_orcids":["https://orcid.org/0000-0001-8546-1778"]},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Strunk","raw_affiliation_strings":["UNIVERSITY OF COLOGNE"],"raw_orcid":"https://orcid.org/0000-0001-8546-1778","affiliations":[{"raw_affiliation_string":"UNIVERSITY OF COLOGNE","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044680360","display_name":"Nikolaus P. Himmelmann","orcid":"https://orcid.org/0000-0002-4385-8395","observed_orcids":["https://orcid.org/0000-0002-4385-8395"]},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nikolaus P. Himmelmann","raw_affiliation_strings":["UNIVERSITY OF COLOGNE"],"raw_orcid":"https://orcid.org/0000-0002-4385-8395","affiliations":[{"raw_affiliation_string":"UNIVERSITY OF COLOGNE","institution_ids":["https://openalex.org/I180923762"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9911999702453613,"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":0.9911999702453613,"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/T10028","display_name":"Topic Modeling","score":0.002300000051036477,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00139999995008111,"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/language-preservation","display_name":"language preservation","score":0.777999997138977},{"id":"https://openalex.org/keywords/endangered-languages","display_name":"endangered languages","score":0.8960000276565552},{"id":"https://openalex.org/keywords/unsupervised-word-segmentation","display_name":"unsupervised word segmentation","score":0.9700000286102295},{"id":"https://openalex.org/keywords/vocabulary-acquisition","display_name":"vocabulary acquisition","score":0.8930000066757202},{"id":"https://openalex.org/keywords/austronesian-languages","display_name":"Austronesian languages","score":0.8840000033378601},{"id":"https://openalex.org/keywords/zipf-s-law","display_name":"Zipf's law","score":0.9210000038146973},{"id":"https://openalex.org/keywords/n-gram-language-models","display_name":"n-gram language models","score":0.7269999980926514},{"id":"https://openalex.org/keywords/lexical-precision","display_name":"lexical precision","score":0.46399998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738947868347168},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.7362532019615173},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.702226996421814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6858280301094055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6357660889625549},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.557668149471283},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.547021746635437},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.4899679720401764},{"id":"https://openalex.org/C2777568999","wikidata":"https://www.wikidata.org/wiki/Q34311","display_name":"Yoruba","level":2,"score":0.42514997720718384},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25236427783966064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12484896183013916},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.703.7460","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.703.7460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nt.uni-paderborn.de/public/pubs/2015/WaHaStHi.pdf","raw_type":"text"},{"id":"mag:2295528958","doi":null,"is_oa":false,"landing_page_url":"https://ipvs.informatik.uni-stuttgart.de/mlr/spp-wordpress/wp-content/uploads/WaHaStHi.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W186138571","https://openalex.org/W1574901103","https://openalex.org/W1886501427","https://openalex.org/W1963727751","https://openalex.org/W2100768664","https://openalex.org/W2107240889","https://openalex.org/W2140991203","https://openalex.org/W2154099718","https://openalex.org/W2289030499"],"related_works":["https://openalex.org/W6992439537","https://openalex.org/W2107240889","https://openalex.org/W4281672062","https://openalex.org/W2033413759","https://openalex.org/W2972572821","https://openalex.org/W2140991203","https://openalex.org/W7034975076","https://openalex.org/W7099933577","https://openalex.org/W1528203680","https://openalex.org/W2117621558"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"show":[4],"that":[5,104],"recently":[6],"developed":[7],"algorithms":[8],"for":[9,18,58,75,126],"unsupervised":[10,27,136,142],"word":[11,28,97,143],"segmentation":[12,29,98,144],"can":[13],"be":[14],"a":[15,33,66],"valuable":[16],"tool":[17],"the":[19,54,105,108,112,118],"documentation":[20],"of":[21,56,61,69,70,114,120],"endangered":[22],"languages.":[23],"We":[24,64],"applied":[25],"an":[26,95],"algorithm":[30,46],"based":[31],"on":[32],"nested":[34],"Pitman-Yor":[35,109],"language":[36,110,140],"model":[37],"to":[38,52],"two":[39],"austronesian":[40],"languages,":[41],"Wooi":[42,76,131],"and":[43,50,72,77,83,117,132],"Waima\u2019a.":[44,133],"The":[45],"was":[47],"then":[48],"modified":[49],"pa-rameterized":[51],"cater":[53],"needs":[55],"linguists":[57],"high":[59],"precision":[60,68],"lexical":[62],"discovery:":[63],"obtained":[65],"lexicon":[67],"69.2%":[71],"67.5":[73],"%":[74],"Waima\u2019a,":[78],"respectively,":[79],"if":[80],"single-letter":[81],"words":[82,84],"found":[85],"less":[86],"than":[87],"three":[88],"times":[89],"were":[90],"discarded.":[91],"A":[92],"comparison":[93],"with":[94],"English":[96],"task":[99],"showed":[100],"comparable":[101],"performance,":[102],"verifying":[103],"assumptions":[106],"under-lying":[107],"model,":[111],"universality":[113],"Zipf\u2019s":[115],"law":[116],"power":[119],"n-gram":[121],"structures,":[122],"do":[123],"also":[124],"hold":[125],"lan-guages":[127],"as":[128,130],"exotic":[129],"Index":[134],"Terms:":[135],"vocabulary":[137],"acquisition,":[138,141],"unsuper-vised":[139]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2016-06-24T00:00:00"}