{"id":"https://openalex.org/W2304025599","doi":null,"title":"Induction of the morphology of natural language : unsupervised morpheme segmentation with application to automatic speech recognition","display_name":"Induction of the morphology of natural language : unsupervised morpheme segmentation with application to automatic speech recognition","publication_year":2006,"publication_date":"2006-06-15","ids":{"openalex":"https://openalex.org/W2304025599","mag":"2304025599"},"language":"en","primary_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/2715","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/2715","pdf_url":"https://aaltodoc.aalto.fi/handle/123456789/2715","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"G5 Artikkeliv\u00e4it\u00f6skirja"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://aaltodoc.aalto.fi/handle/123456789/2715","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061159001","display_name":"Mathias Creutz","orcid":"https://orcid.org/0000-0003-1862-4172","observed_orcids":["https://orcid.org/0000-0003-1862-4172"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mathias Creutz","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1862-4172","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5061159001"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":null,"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":0.9901999831199646,"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":0.9901999831199646,"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":0.005900000222027302,"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/T12031","display_name":"Speech and dialogue systems","score":0.0008999999845400453,"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/morpheme-segmentation","display_name":"morpheme segmentation","score":0.9559999704360962},{"id":"https://openalex.org/keywords/morfessor","display_name":"Morfessor","score":0.972000002861023},{"id":"https://openalex.org/keywords/word-segmentation","display_name":"word segmentation","score":0.875},{"id":"https://openalex.org/keywords/finnish","display_name":"Finnish language","score":0.628000020980835},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.8679999709129333},{"id":"https://openalex.org/keywords/compounding","display_name":"compounding","score":0.4269999861717224},{"id":"https://openalex.org/keywords/inflection","display_name":"inflection","score":0.6449999809265137},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.6620000004768372},{"id":"https://openalex.org/keywords/large-vocabulary-speech-recognition","display_name":"large vocabulary speech recognition","score":0.6740000247955322}],"concepts":[{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.92610764503479},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7088276147842407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6885614991188049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6823689341545105},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5441620349884033},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5141921043395996},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.459847092628479},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4206914007663727},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.41323965787887573},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3224616050720215},{"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":"pmh:oai:aaltodoc.aalto.fi:123456789/2715","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/2715","pdf_url":"https://aaltodoc.aalto.fi/handle/123456789/2715","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"G5 Artikkeliv\u00e4it\u00f6skirja"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.100.3944","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.100.3944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lib.tkk.fi/Diss/2006/isbn9512282119/isbn9512282119.pdf","raw_type":"text"},{"id":"mag:2304025599","doi":null,"is_oa":false,"landing_page_url":"http://lib.tkk.fi/Diss/2006/isbn9512282119/isbn9512282119.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":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/2715","doi":null,"is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/2715","pdf_url":"https://aaltodoc.aalto.fi/handle/123456789/2715","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"G5 Artikkeliv\u00e4it\u00f6skirja"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2304025599.pdf","grobid_xml":"https://content.openalex.org/works/W2304025599.grobid-xml"},"referenced_works_count":169,"referenced_works":["https://openalex.org/W813000","https://openalex.org/W3405206","https://openalex.org/W4930780","https://openalex.org/W10704533","https://openalex.org/W57918715","https://openalex.org/W59625463","https://openalex.org/W65738273","https://openalex.org/W88081813","https://openalex.org/W98065071","https://openalex.org/W103463988","https://openalex.org/W106471163","https://openalex.org/W111337582","https://openalex.org/W112233275","https://openalex.org/W115200403","https://openalex.org/W138138553","https://openalex.org/W139293362","https://openalex.org/W148400104","https://openalex.org/W154368987","https://openalex.org/W163823652","https://openalex.org/W164767329","https://openalex.org/W170307911","https://openalex.org/W201288405","https://openalex.org/W203298151","https://openalex.org/W204603808","https://openalex.org/W262058279","https://openalex.org/W1485243506","https://openalex.org/W1495314497","https://openalex.org/W1498096105","https://openalex.org/W1503913248","https://openalex.org/W1509106210","https://openalex.org/W1523886368","https://openalex.org/W1526103475","https://openalex.org/W1528203680","https://openalex.org/W1530250655","https://openalex.org/W1538973122","https://openalex.org/W1545666865","https://openalex.org/W1548802052","https://openalex.org/W1560013842","https://openalex.org/W1561310868","https://openalex.org/W1571404427","https://openalex.org/W1579838312","https://openalex.org/W1580142630","https://openalex.org/W1586407478","https://openalex.org/W1600529453","https://openalex.org/W1601995877","https://openalex.org/W1603076355","https://openalex.org/W1616871572","https://openalex.org/W1631260214","https://openalex.org/W1632114991","https://openalex.org/W1679913846","https://openalex.org/W1683106298","https://openalex.org/W1687743765","https://openalex.org/W1707124376","https://openalex.org/W1727944201","https://openalex.org/W1749358154","https://openalex.org/W1886814818","https://openalex.org/W1934041838","https://openalex.org/W1955233831","https://openalex.org/W1956785191","https://openalex.org/W1971074050","https://openalex.org/W1978470410","https://openalex.org/W1983311927","https://openalex.org/W1984676939","https://openalex.org/W1987902506","https://openalex.org/W1988013505","https://openalex.org/W1989705153","https://openalex.org/W1991133427","https://openalex.org/W1996903695","https://openalex.org/W1997404989","https://openalex.org/W1997658299","https://openalex.org/W2007976151","https://openalex.org/W2010910318","https://openalex.org/W2014303786","https://openalex.org/W2016630033","https://openalex.org/W2020089859","https://openalex.org/W2022201897","https://openalex.org/W2022817031","https://openalex.org/W2029948425","https://openalex.org/W2034915529","https://openalex.org/W2039660096","https://openalex.org/W2042143122","https://openalex.org/W2042783153","https://openalex.org/W2045656233","https://openalex.org/W2046932483","https://openalex.org/W2047603832","https://openalex.org/W2049633694","https://openalex.org/W2053782355","https://openalex.org/W2054658115","https://openalex.org/W2056250865","https://openalex.org/W2056357537","https://openalex.org/W2056573988","https://openalex.org/W2059842576","https://openalex.org/W2062837929","https://openalex.org/W2064043696","https://openalex.org/W2068782468","https://openalex.org/W2069330295","https://openalex.org/W2070554026","https://openalex.org/W2071772291","https://openalex.org/W2074525598","https://openalex.org/W2074546930","https://openalex.org/W2082092506","https://openalex.org/W2083698190","https://openalex.org/W2086699924","https://openalex.org/W2088857750","https://openalex.org/W2089497633","https://openalex.org/W2096204319","https://openalex.org/W2097835057","https://openalex.org/W2100373303","https://openalex.org/W2100653055","https://openalex.org/W2101711363","https://openalex.org/W2102098892","https://openalex.org/W2103777995","https://openalex.org/W2105684587","https://openalex.org/W2110381504","https://openalex.org/W2110485445","https://openalex.org/W2111305191","https://openalex.org/W2112874453","https://openalex.org/W2113123406","https://openalex.org/W2114986384","https://openalex.org/W2115054880","https://openalex.org/W2115282603","https://openalex.org/W2115867364","https://openalex.org/W2118714763","https://openalex.org/W2119423321","https://openalex.org/W2121227244","https://openalex.org/W2122410182","https://openalex.org/W2124776405","https://openalex.org/W2125971872","https://openalex.org/W2126016680","https://openalex.org/W2130454225","https://openalex.org/W2134237567","https://openalex.org/W2135508918","https://openalex.org/W2140679639","https://openalex.org/W2141684702","https://openalex.org/W2142384583","https://openalex.org/W2142635246","https://openalex.org/W2146855196","https://openalex.org/W2147152072","https://openalex.org/W2147354085","https://openalex.org/W2148398960","https://openalex.org/W2148603752","https://openalex.org/W2158195707","https://openalex.org/W2161952424","https://openalex.org/W2162161511","https://openalex.org/W2166391802","https://openalex.org/W2170521549","https://openalex.org/W2170716495","https://openalex.org/W2171026506","https://openalex.org/W2172193264","https://openalex.org/W2185720888","https://openalex.org/W2275055927","https://openalex.org/W2300419000","https://openalex.org/W2315366077","https://openalex.org/W2316710478","https://openalex.org/W2339534148","https://openalex.org/W2420792277","https://openalex.org/W2432567885","https://openalex.org/W2571532437","https://openalex.org/W2725592455","https://openalex.org/W2728904056","https://openalex.org/W2796493717","https://openalex.org/W2882319491","https://openalex.org/W2884980639","https://openalex.org/W2979401726","https://openalex.org/W3031528655","https://openalex.org/W3043710305","https://openalex.org/W3140968660","https://openalex.org/W3183153947","https://openalex.org/W4253654031"],"related_works":["https://openalex.org/W4249773576","https://openalex.org/W7099914471","https://openalex.org/W3183153947","https://openalex.org/W2117621558","https://openalex.org/W1970887833","https://openalex.org/W201532657","https://openalex.org/W40022206","https://openalex.org/W1905100302","https://openalex.org/W7098193639","https://openalex.org/W1577204225"],"abstract_inverted_index":{"In":[0,196,231,296],"order":[1],"to":[2,31,110,198,233,270,302],"develop":[3],"computer":[4],"applications":[5],"that":[6,114,243],"successfully":[7],"process":[8],"natural":[9],"language":[10],"data":[11],"(text":[12],"and":[13,22,70,211,225,277,280,341],"speech),":[14],"one":[15],"needs":[16],"good":[17],"models":[18],"of":[19,24,37,53,64,68,106,119,125,137,167,173,176,186,208,215,253,275,285,314,335,339],"the":[20,41,66,116,120,168,177,251,254,315],"vocabulary":[21,291],"grammar":[23,242],"as":[25,28,152,229,282,312],"many":[26],"languages":[27],"possible.":[29],"According":[30],"standard":[32],"linguistic":[33,271,307,321],"theory,":[34],"words":[35,124,206,279],"consist":[36],"morphemes,":[38,65],"which":[39,78,249],"are":[40,80,91],"smallest":[42],"individually":[43],"meaningful":[44],"elements":[45],"in":[46,95,123,142,260,264,326],"a":[47,61,112,134,153,209,219,240,283,286,327,336],"language.":[48,127],"Since":[49],"an":[50,143],"immense":[51],"number":[52,214,338],"word":[54,73,101,193,235,343],"forms":[55,74],"can":[56,204],"be":[57],"constructed":[58],"by":[59,268],"combining":[60],"limited":[62],"set":[63],"capability":[67],"understanding":[69],"producing":[71],"new":[72],"depends":[75],"on":[76,163,319],"knowing":[77],"morphemes":[79],"involved":[81],"(e.g.,":[82],"\"water,":[83],"water+s,":[84],"water+y,":[85],"water+less,":[86],"water+less+ness,":[87],"sea+water\").":[88],"Morpheme":[89],"boundaries":[90,122],"not":[92,161],"normally":[93],"marked":[94],"text":[96],"unless":[97],"they":[98],"coincide":[99],"with":[100,223],"boundaries.":[102],"The":[103,128,306],"main":[104],"objective":[105],"this":[107,265],"thesis":[108],"is":[109,150,218,258,300],"devise":[111],"method":[113,129],"discovers":[115],"likely":[117],"locations":[118],"morpheme":[121,273],"any":[126],"proposed,":[130],"called":[131,331],"Morfessor,":[132],"learns":[133,239],"simple":[135,241],"model":[136],"concatenative":[138],"morphology":[139,190,200],"(word":[140],"forming)":[141],"unsupervised":[144,188],"manner":[145],"from":[146],"plain":[147],"text.":[148,179],"Morfessor":[149,180,203,238,257,299],"formulated":[151],"Bayesian,":[154],"probabilistic":[155],"model.":[156],"That":[157],"is,":[158],"it":[159],"does":[160],"rely":[162],"predefined":[164],"grammatical":[165],"rules":[166],"language,":[169],"but":[170],"makes":[171],"use":[172],"statistical":[174],"properties":[175],"input":[178],"situates":[181],"itself":[182],"between":[183],"two":[184,261],"types":[185],"existing":[187,199,234,320],"methods:":[189],"learning":[191,201],"vs.":[192],"segmentation":[194,236],"algorithms.":[195],"contrast":[197,232],"algorithms,":[202],"handle":[205],"consisting":[207],"varying":[210],"possibly":[212],"high":[213],"morphemes.":[216],"This":[217,323],"requirement":[220],"for":[221],"coping":[222],"highly-inflecting":[224],"compounding":[226],"languages,":[227],"such":[228],"Finnish.":[230],"methods,":[237],"takes":[244],"into":[245],"account":[246],"sequential":[247],"dependencies,":[248],"improves":[250],"quality":[252],"proposed":[255],"segmentations.":[256],"evaluated":[259],"complementary":[262],"ways":[263],"work:":[266],"directly":[267],"comparing":[269],"reference":[272,308],"segmentations":[274,309],"Finnish":[276,292,340],"English":[278,342],"indirectly":[281],"component":[284],"large":[287,337],"(or":[288],"virtually":[289],"unlimited)":[290],"speech":[293],"recognition":[294],"system.":[295],"both":[297],"cases,":[298],"shown":[301],"outperform":[303],"state-of-the-art":[304],"solutions.":[305],"were":[310],"produced":[311],"part":[313],"current":[316],"work,":[317],"based":[318],"resources.":[322],"has":[324],"resulted":[325],"morphological":[328],"gold":[329],"standard,":[330],"Hutmegs,":[332],"containing":[333],"analyses":[334],"forms.":[344]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}