{"id":"https://openalex.org/W1978633790","doi":"https://doi.org/10.1145/1731035.1731038","title":"Inducing Morphemes Using Light Knowledge","display_name":"Inducing Morphemes Using Light Knowledge","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W1978633790","doi":"https://doi.org/10.1145/1731035.1731038","mag":"1978633790"},"language":"en","primary_location":{"id":"doi:10.1145/1731035.1731038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1731035.1731038","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-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/A5026577646","display_name":"Michael Tepper","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Tepper","raw_affiliation_strings":["Department of Linguistics, University of Washington","Department of Linguistics, University of Washington#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Department of Linguistics, University of Washington#TAB#","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676785","display_name":"Fei Xia","orcid":"https://orcid.org/0000-0003-4343-1444"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Xia","raw_affiliation_strings":["Department of Linguistics, University of Washington","Department of Linguistics, University of Washington#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Department of Linguistics, University of Washington#TAB#","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026577646"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":2.00409607,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88436869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":"1","first_page":"1","last_page":"38"},"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":0.9988999962806702,"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":0.9851999878883362,"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","display_name":"Morpheme","score":0.8511747121810913},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7632882595062256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6815632581710815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6040980815887451},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5291823744773865},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5260003805160522},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.501060962677002},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.44539785385131836},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.41629576683044434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39339208602905273},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1937897801399231}],"concepts":[{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.8511747121810913},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7632882595062256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6815632581710815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6040980815887451},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5291823744773865},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5260003805160522},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.501060962677002},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.44539785385131836},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.41629576683044434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39339208602905273},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1937897801399231},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1731035.1731038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1731035.1731038","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W101793699","https://openalex.org/W111337582","https://openalex.org/W157143106","https://openalex.org/W201288405","https://openalex.org/W201532657","https://openalex.org/W593009930","https://openalex.org/W1513168562","https://openalex.org/W1530250655","https://openalex.org/W1543870019","https://openalex.org/W1586407478","https://openalex.org/W1598851216","https://openalex.org/W1970887833","https://openalex.org/W1983311927","https://openalex.org/W2013833248","https://openalex.org/W2034915529","https://openalex.org/W2047603832","https://openalex.org/W2074525598","https://openalex.org/W2085247339","https://openalex.org/W2088857750","https://openalex.org/W2097835057","https://openalex.org/W2098019960","https://openalex.org/W2101711363","https://openalex.org/W2114986384","https://openalex.org/W2116512888","https://openalex.org/W2117621558","https://openalex.org/W2119423321","https://openalex.org/W2142795932","https://openalex.org/W2152374979","https://openalex.org/W2304025599","https://openalex.org/W2315366077","https://openalex.org/W2380230465","https://openalex.org/W2542843105","https://openalex.org/W2598654328","https://openalex.org/W2725592455","https://openalex.org/W2728904056","https://openalex.org/W2788854033","https://openalex.org/W2797528156","https://openalex.org/W3036063182","https://openalex.org/W4301420590","https://openalex.org/W6630740198","https://openalex.org/W6809344118","https://openalex.org/W7083093950"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2061970941","https://openalex.org/W2144561170","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2785359773","https://openalex.org/W2058548953","https://openalex.org/W2362013696"],"abstract_inverted_index":{"Allomorphic":[0],"variation,":[1],"or":[2],"form":[3,38],"variation":[4],"among":[5],"morphs":[6],"with":[7,58],"the":[8,37,83,153,159,168,178],"same":[9],"meaning,":[10],"is":[11,113,140],"a":[12,25,30,74,122,134,189],"stumbling":[13],"block":[14],"to":[15,43,60,96,117],"morphological":[16],"induction":[17],"(MI).":[18],"To":[19,77,128],"address":[20],"this":[21],"problem,":[22],"we":[23,52,72,80,125,174],"present":[24],"hybrid":[26],"approach":[27,155],"that":[28,124],"uses":[29],"small":[31],"amount":[32],"of":[33,39,56,136],"linguistic":[34],"knowledge":[35],"in":[36],"orthographic":[40,138],"rewrite":[41],"rules":[42,95,139],"help":[44],"refine":[45],"an":[46,64],"existing":[47,65],"MI-produced":[48],"segmentation.":[49,76],"Using":[50],"rules,":[51],"derive":[53],"underlying":[54,99],"analyses":[55,100,130],"morphs---generalized":[57],"respect":[59],"contextual":[61],"spelling":[62],"differences---from":[63],"surface":[66,102],"morph":[67],"segmentation,":[68],"and":[69,88,120,150,163],"from":[70,101],"these":[71],"learn":[73,78],"morpheme-level":[75],"morphemes,":[79],"have":[81],"extended":[82],"Morfessor":[84,108],"segmentation":[85,105],"algorithm":[86],"[Creutz":[87],"Lagus":[89],"2004;":[90],"2005;":[91],"2006]":[92],"by":[93,107],"using":[94],"infer":[97],"possible":[98],"segmentations.":[103],"A":[104],"produced":[106],"Categories-MAP":[109],"Software":[110],"v.":[111],"0.9.2":[112],"used":[114],"as":[115,121],"input":[116],"our":[118,132,186],"procedure":[119,143],"baseline":[123,154],"evaluate":[126],"against.":[127],"suggest":[129],"for":[131,148,183],"procedure,":[133],"set":[135],"language-specific":[137],"needed.":[141],"Our":[142],"has":[144],"yielded":[145],"promising":[146],"improvements":[147],"English":[149],"Turkish":[151],"over":[152,177],"when":[156],"tested":[157],"on":[158],"Morpho":[160,169],"Challenge":[161,170],"2005":[162],"2007":[164,171],"style":[165],"evaluations.":[166],"On":[167],"test":[172],"evaluation,":[173],"report":[175],"gains":[176],"current":[179],"best":[180],"unsupervised":[181],"contestant":[182],"Turkish,":[184],"where":[185],"technique":[187],"shows":[188],"2.5%":[190],"absolute":[191],"F":[192],"-score":[193],"improvement.":[194]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}