{"id":"https://openalex.org/W3040765441","doi":"https://doi.org/10.1017/s1351324920000406","title":"Incorporating word embeddings in unsupervised morphological segmentation","display_name":"Incorporating word embeddings in unsupervised morphological segmentation","publication_year":2020,"publication_date":"2020-07-10","ids":{"openalex":"https://openalex.org/W3040765441","doi":"https://doi.org/10.1017/s1351324920000406","mag":"3040765441"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324920000406","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000406","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.rug.nl/en/publications/6e7208fc-3ce5-4434-b044-cc87a4d6bf7e","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063061204","display_name":"Ahmet \u00dcst\u00fcn","orcid":"https://orcid.org/0000-0002-1640-4291"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ahmet \u00dcst\u00fcn","raw_affiliation_strings":["The University of Groningen, Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Groningen, Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046915242","display_name":"Burcu Can","orcid":"https://orcid.org/0000-0002-1700-0395"},"institutions":[{"id":"https://openalex.org/I66514158","display_name":"Hacettepe University","ror":"https://ror.org/04kwvgz42","country_code":"TR","type":"education","lineage":["https://openalex.org/I66514158"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Burcu Can","raw_affiliation_strings":["Department of Computer Engineering, Hacettepe University, Ankara, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-1700-0395","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Hacettepe University, Ankara, Turkey","institution_ids":["https://openalex.org/I66514158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046915242"],"corresponding_institution_ids":["https://openalex.org/I66514158"],"apc_list":{"value":3160,"currency":"USD","value_usd":3160},"apc_paid":null,"fwci":0.2841,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67719744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"27","issue":"5","first_page":"609","last_page":"629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9986000061035156,"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":0.893512487411499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6988160610198975},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6925150752067566},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6918590068817139},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6358681321144104},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.5809242129325867},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5188782811164856},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.499086856842041},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49732115864753723},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.4618040919303894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4257327616214752},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4104751646518707},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.3511381149291992},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08327886462211609},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06716486811637878},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06622034311294556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.893512487411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6988160610198975},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6925150752067566},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6918590068817139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6358681321144104},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.5809242129325867},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5188782811164856},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.499086856842041},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49732115864753723},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4618040919303894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4257327616214752},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4104751646518707},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.3511381149291992},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08327886462211609},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06716486811637878},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06622034311294556},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1017/s1351324920000406","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000406","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:pure.rug.nl:openaire/6e7208fc-3ce5-4434-b044-cc87a4d6bf7e","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/6e7208fc-3ce5-4434-b044-cc87a4d6bf7e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ustun, A & Can, B 2021, 'Incorporating word embeddings in unsupervised morphological segmentation', Natural Language Engineering, vol. 27, no. 5, pp. 609-629. https://doi.org/10.1017/S1351324920000406","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:wlv.openrepository.com:2436/623615","is_oa":true,"landing_page_url":"http://hdl.handle.net/2436/623615","pdf_url":null,"source":{"id":"https://openalex.org/S4306401000","display_name":"Wolverhampton Intellectual Repository and E-Theses (University of Wolverhampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119664326","host_organization_name":"University of Wolverhampton","host_organization_lineage":["https://openalex.org/I119664326"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"2020","raw_type":"Journal article"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:openaire/6e7208fc-3ce5-4434-b044-cc87a4d6bf7e","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/6e7208fc-3ce5-4434-b044-cc87a4d6bf7e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ustun, A & Can, B 2021, 'Incorporating word embeddings in unsupervised morphological segmentation', Natural Language Engineering, vol. 27, no. 5, pp. 609-629. https://doi.org/10.1017/S1351324920000406","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W201532657","https://openalex.org/W1503913248","https://openalex.org/W1583936759","https://openalex.org/W1614298861","https://openalex.org/W1839584883","https://openalex.org/W1983311927","https://openalex.org/W2020999234","https://openalex.org/W2053306448","https://openalex.org/W2070554026","https://openalex.org/W2101711363","https://openalex.org/W2117621558","https://openalex.org/W2130042265","https://openalex.org/W2139090905","https://openalex.org/W2159399018","https://openalex.org/W2167419393","https://openalex.org/W2179974023","https://openalex.org/W2294970769","https://openalex.org/W2417763662","https://openalex.org/W2493916176","https://openalex.org/W2523561069","https://openalex.org/W2795958200","https://openalex.org/W2886167250","https://openalex.org/W2950577311","https://openalex.org/W2964005834","https://openalex.org/W3183153947","https://openalex.org/W4251556668"],"related_works":["https://openalex.org/W1503532423","https://openalex.org/W2150865841","https://openalex.org/W1967494390","https://openalex.org/W2138865713","https://openalex.org/W3013496002","https://openalex.org/W2465363361","https://openalex.org/W2896820906","https://openalex.org/W4284711868","https://openalex.org/W2101542441","https://openalex.org/W2021166481"],"abstract_inverted_index":{"Abstract":[0],"We":[1,23,95],"investigate":[2],"the":[3],"usage":[4],"of":[5,68],"semantic":[6,41,104],"information":[7,42],"for":[8,76,92,98,111,121],"morphological":[9,89],"segmentation":[10,90],"since":[11],"words":[12],"that":[13,82],"are":[14],"derived":[15],"from":[16,44],"each":[17],"other":[18,108,123],"will":[19],"remain":[20],"semantically":[21],"related.":[22],"use":[24],"mathematical":[25],"models":[26,110,116],"such":[27],"as":[28],"maximum":[29,34],"likelihood":[30],"estimate":[31,37],"(MLE)":[32],"and":[33,62,101],"a":[35,65],"posteriori":[36],"(MAP)":[38],"by":[39],"incorporating":[40],"obtained":[43],"dense":[45,84],"word":[46,74],"vector":[47,85],"representations.":[48],"Our":[49,103,114],"approach":[50],"does":[51],"not":[52],"require":[53,63],"any":[54,122],"annotated":[55],"data":[56,70],"which":[57],"make":[58],"it":[59],"fully":[60],"unsupervised":[61,109],"only":[64],"small":[66],"amount":[67],"raw":[69],"together":[71],"with":[72,126],"pretrained":[73],"embeddings":[75],"training":[77],"purposes.":[78],"The":[79],"results":[80,97],"show":[81],"using":[83],"representations":[86],"helps":[87],"in":[88],"especially":[91],"low-resource":[93,124],"languages.":[94],"present":[96],"Turkish,":[99],"English,":[100],"German.":[102],"MLE":[105],"model":[106],"outperforms":[107],"Turkish":[112],"language.":[113],"proposed":[115],"could":[117],"be":[118],"also":[119],"used":[120],"language":[125],"concatenative":[127],"morphology.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-09-01T08:31:24.195828","created_date":"2025-10-10T00:00:00"}