{"id":"https://openalex.org/W1727944201","doi":"https://doi.org/10.3115/1118647.1118653","title":"Unsupervised discovery of morphologically related words based on orthographic and semantic similarity","display_name":"Unsupervised discovery of morphologically related words based on orthographic and semantic similarity","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W1727944201","doi":"https://doi.org/10.3115/1118647.1118653","mag":"1727944201"},"language":"en","primary_location":{"id":"doi:10.3115/1118647.1118653","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118647.1118653","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1118653&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 workshop on Morphological and phonological learning  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1118653&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038612405","display_name":"Marco Baroni","orcid":"https://orcid.org/0000-0001-5066-3580"},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Marco Baroni","raw_affiliation_strings":["\u00d6FAI, Austria#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00d6FAI, Austria#TAB#","institution_ids":["https://openalex.org/I161878677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050235805","display_name":"Johannes Matiasek","orcid":null},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Johannes Matiasek","raw_affiliation_strings":["\u00d6FAI, Austria#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00d6FAI, Austria#TAB#","institution_ids":["https://openalex.org/I161878677"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090301030","display_name":"Harald Trost","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harald Trost","raw_affiliation_strings":["IMKAI, Austria#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMKAI, Austria#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.971,"has_fulltext":true,"cited_by_count":114,"citation_normalized_percentile":{"value":0.96291271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"6","issue":null,"first_page":"48","last_page":"57"},"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":0.9993000030517578,"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":0.9972000122070312,"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/substring","display_name":"Substring","score":0.765557050704956},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7550354599952698},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6915920972824097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6914100646972656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6831806898117065},{"id":"https://openalex.org/keywords/affix","display_name":"Affix","score":0.6722371578216553},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.5934838652610779},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5821354389190674},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.5539414882659912},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5210872888565063},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5191613435745239},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4326930046081543},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38196897506713867},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2813732326030731},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.12003591656684875},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10346168279647827}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.765557050704956},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7550354599952698},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6915920972824097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6914100646972656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6831806898117065},{"id":"https://openalex.org/C2778428490","wikidata":"https://www.wikidata.org/wiki/Q62155","display_name":"Affix","level":2,"score":0.6722371578216553},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.5934838652610779},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5821354389190674},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.5539414882659912},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5210872888565063},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5191613435745239},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4326930046081543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38196897506713867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2813732326030731},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.12003591656684875},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10346168279647827},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1118647.1118653","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118647.1118653","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1118653&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 workshop on Morphological and phonological learning  -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.6.9887","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.6.9887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.oefai.at/cgi-bin/get-tr?paper=oefai-tr-2002-21.ps.gz","raw_type":"text"},{"id":"pmh:oai:iris.unitn.it:11572/17008","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/17008","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3115/1118647.1118653","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118647.1118653","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1118653&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 workshop on Morphological and phonological learning  -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323991","display_name":"Bundesministerium f\u00fcr Bildung, Wissenschaft und Kultur","ror":"https://ror.org/03rrfep50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1727944201.pdf","grobid_xml":"https://content.openalex.org/works/W1727944201.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W152655843","https://openalex.org/W182831726","https://openalex.org/W1574901103","https://openalex.org/W1579838312","https://openalex.org/W1593045043","https://openalex.org/W1996903695","https://openalex.org/W1997658299","https://openalex.org/W2007780422","https://openalex.org/W2047603832","https://openalex.org/W2101711363","https://openalex.org/W2111111410","https://openalex.org/W2114986384","https://openalex.org/W2121227244","https://openalex.org/W2134955506","https://openalex.org/W2141684702","https://openalex.org/W2166925181","https://openalex.org/W4233950802","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2136519138","https://openalex.org/W1989944203","https://openalex.org/W1991762134","https://openalex.org/W1998479724","https://openalex.org/W3034305000","https://openalex.org/W2546839375","https://openalex.org/W3082647531","https://openalex.org/W2963185483","https://openalex.org/W3127593639","https://openalex.org/W2999485669"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2,6],"algorithm":[3,26],"that":[4,37],"takes":[5],"unannotated":[7],"corpus":[8],"as":[9,22,83],"its":[10,23],"input,":[11],"and":[12,41,55,89,113],"returns":[13],"a":[14,71,117],"ranked":[15,111],"list":[16],"of":[17,51,62,79,98,101,109,116,120,123],"probable":[18],"morphologically":[19,30],"related":[20,31],"pairs":[21,32,36,103],"output.":[24],"The":[25,65],"tries":[27],"to":[28],"discover":[29],"by":[33,127],"looking":[34],"for":[35],"are":[38],"both":[39,95],"orthographically":[40],"semantically":[42],"similar,":[43],"where":[44],"orthographic":[45],"similarity":[46,57],"is":[47,58],"measured":[48,59],"in":[49,60,96,114],"terms":[50,61,97,115],"minimum":[52],"edit":[53],"distance,":[54],"semantic":[56],"mutual":[63],"information.":[64],"procedure":[66],"does":[67],"not":[68],"rely":[69],"on":[70,76],"morpheme":[72],"concatenation":[73],"model,":[74],"nor":[75],"distributional":[77],"properties":[78],"word":[80],"substrings":[81],"(such":[82],"affix":[84],"frequency).":[85],"Experiments":[86],"with":[87],"German":[88],"English":[90],"input":[91],"give":[92],"encouraging":[93],"results,":[94],"precision":[99],"(proportion":[100],"good":[102],"found":[104],"at":[105],"various":[106],"cutoff":[107],"points":[108],"the":[110,121,128],"list),":[112],"qualitative":[118],"analysis":[119],"types":[122],"morphological":[124],"patterns":[125],"discovered":[126],"algorithm.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}