{"id":"https://openalex.org/W2739845275","doi":"https://doi.org/10.18653/v1/e17-1032","title":"From Segmentation to Analyses: a Probabilistic Model for Unsupervised Morphology Induction","display_name":"From Segmentation to Analyses: a Probabilistic Model for Unsupervised Morphology Induction","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2739845275","doi":"https://doi.org/10.18653/v1/e17-1032","mag":"2739845275"},"language":"en","primary_location":{"id":"doi:10.18653/v1/e17-1032","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-1032","pdf_url":"https://www.aclweb.org/anthology/E17-1032.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/E17-1032.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036980337","display_name":"Toms Bergmanis","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Toms Bergmanis","raw_affiliation_strings":["School of Informatics University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5036980337"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8388328552246094},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7068781852722168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6287645101547241},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6043550968170166},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5965348482131958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5950493216514587},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5542994141578674},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5342760682106018},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48418429493904114},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4482668340206146},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44150394201278687},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.43308937549591064},{"id":"https://openalex.org/keywords/morphology","display_name":"Morphology (biology)","score":0.42185813188552856},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2696771025657654},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13461971282958984}],"concepts":[{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.8388328552246094},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7068781852722168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6287645101547241},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6043550968170166},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5965348482131958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5950493216514587},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5542994141578674},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5342760682106018},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48418429493904114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4482668340206146},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44150394201278687},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.43308937549591064},{"id":"https://openalex.org/C499950583","wikidata":"https://www.wikidata.org/wiki/Q183252","display_name":"Morphology (biology)","level":2,"score":0.42185813188552856},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2696771025657654},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13461971282958984},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/e17-1032","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-1032","pdf_url":"https://www.aclweb.org/anthology/E17-1032.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/74450287-2524-434a-ab28-15587cc2baca","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/74450287-2524-434a-ab28-15587cc2baca","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bergmanis, T & Goldwater, S 2017, From Segmentation to Analyses: A Probabilistic Model for Unsupervised Morphology Induction. in Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. pp. 337-346, The 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, 3/04/17. < https://aclweb.org/anthology/E/E17/E17-1032 >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/74450287-2524-434a-ab28-15587cc2baca","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/74450287-2524-434a-ab28-15587cc2baca","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/e17-1032","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-1032","pdf_url":"https://www.aclweb.org/anthology/E17-1032.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2739845275.pdf","grobid_xml":"https://content.openalex.org/works/W2739845275.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W309335912","https://openalex.org/W1614298861","https://openalex.org/W1616871572","https://openalex.org/W1727944201","https://openalex.org/W1839584883","https://openalex.org/W1975638594","https://openalex.org/W2005126631","https://openalex.org/W2039660096","https://openalex.org/W2053306448","https://openalex.org/W2101711363","https://openalex.org/W2103152638","https://openalex.org/W2114003811","https://openalex.org/W2130935327","https://openalex.org/W2137807925","https://openalex.org/W2141684702","https://openalex.org/W2172709584","https://openalex.org/W2179974023","https://openalex.org/W2251667755","https://openalex.org/W2298625384","https://openalex.org/W2398428910","https://openalex.org/W2950577311","https://openalex.org/W4249773576"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W2061970941","https://openalex.org/W2144561170","https://openalex.org/W4286983112","https://openalex.org/W3196812748"],"abstract_inverted_index":{"A":[0],"major":[1],"motivation":[2],"for":[3,135],"unsupervised":[4],"morphological":[5],"analysis":[6],"is":[7,129],"to":[8,54,67,83],"reduce":[9],"the":[10,40,45,59,70,119],"sparse":[11,41],"data":[12,42],"problem":[13,43],"in":[14],"under-resourced":[15],"languages.":[16],"Most":[17],"previous":[18],"work":[19],"focuses":[20],"on":[21,106,130],"segmenting":[22],"surface":[23,34],"forms":[24],"into":[25],"their":[26],"constituent":[27],"morphs":[28],"(e.g.,":[29],"taking:":[30],"tak":[31],"+ing),":[32,78],"but":[33],"form":[35],"segmentation":[36],"does":[37],"not":[38,52,65],"solve":[39],"as":[44],"analyses":[46,63],"of":[47,73,110,122],"take":[48],"and":[49],"taking":[50],"are":[51,64,80],"connected":[53],"each":[55],"other.":[56],"We":[57],"extend":[58],"MorphoChains":[60],"system":[61,99,128],"These":[62],"required":[66],"use":[68],"all":[69],"orthographic":[71],"material":[72,86],"a":[74,101],"word":[75],"(stopping:":[76],"stop":[77],"nor":[79],"they":[81],"limited":[82],"only":[84],"that":[85],"(acidified:":[87],"acid":[88],"+ify":[89],"+ed).":[90],"On":[91],"average":[92,131],"across":[93],"six":[94],"typologically":[95],"varied":[96],"languages":[97],"our":[98,127],"has":[100],"similar":[102],"or":[103],"better":[104],"F-score":[105],"EMMA":[107],"(a":[108],"measure":[109],"underlying":[111],"morpheme":[112],"accuracy)":[113],"than":[114,134],"three":[115],"strong":[116],"baselines;":[117],"moreover,":[118],"total":[120],"number":[121],"distinct":[123],"morphemes":[124],"identified":[125],"by":[126],"12.8%":[132],"lower":[133],"Morfessor":[136]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}