{"id":"https://openalex.org/W2130935327","doi":"https://doi.org/10.1162/tacl_a_00225","title":"Minimally-Supervised Morphological Segmentation using Adaptor Grammars","display_name":"Minimally-Supervised Morphological Segmentation using Adaptor Grammars","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2130935327","doi":"https://doi.org/10.1162/tacl_a_00225","mag":"2130935327"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00225","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00225","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00225","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00225","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035358986","display_name":"Kairit Sirts","orcid":"https://orcid.org/0000-0001-7388-2583"},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Kairit Sirts","raw_affiliation_strings":["Institute of Cybernetics, Tallinn University of Technology,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Cybernetics, Tallinn University of Technology,","institution_ids":["https://openalex.org/I111112146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics, The University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, The University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8148,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.96633743,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"1","issue":null,"first_page":"255","last_page":"266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9987000226974487,"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":0.8099574446678162},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.690686821937561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6520713567733765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5753885507583618},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5467553734779358},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5404262542724609},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4959810674190521},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4380582571029663},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4061155915260315},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36305853724479675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099574446678162},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.690686821937561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6520713567733765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5753885507583618},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5467553734779358},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5404262542724609},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4959810674190521},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4380582571029663},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4061155915260315},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36305853724479675},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/tacl_a_00225","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00225","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00225","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.297.6644","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.6644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/sgwater/papers/tacl13-AGMorph.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.6074","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.6074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.transacl.org/wp-content/uploads/2013/05/paper255.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:0728b4d61cb547d682c1e261b5137293","is_oa":false,"landing_page_url":"https://doaj.org/article/0728b4d61cb547d682c1e261b5137293","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 1 (2021)","raw_type":"article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/e5fc4878-09a7-4307-9b93-8934e8059e8b","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/minimallysupervised-morphological-segmentation-using-adaptor-grammars(e5fc4878-09a7-4307-9b93-8934e8059e8b).html","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00225","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00225","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00225","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322700","display_name":"Hariduse Infotehnoloogia Sihtasutus","ror":"https://ror.org/02e2avb86"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2130935327.pdf","grobid_xml":"https://content.openalex.org/works/W2130935327.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1650210997","https://openalex.org/W1905100302","https://openalex.org/W1942266131","https://openalex.org/W1969608442","https://openalex.org/W1975638594","https://openalex.org/W2004353685","https://openalex.org/W2048500237","https://openalex.org/W2053306448","https://openalex.org/W2087309226","https://openalex.org/W2101711363","https://openalex.org/W2101717196","https://openalex.org/W2114003811","https://openalex.org/W2116211107","https://openalex.org/W2117126688","https://openalex.org/W2122093182","https://openalex.org/W2126449874","https://openalex.org/W2126953647","https://openalex.org/W2151194837","https://openalex.org/W2159399018","https://openalex.org/W2179974023","https://openalex.org/W2726684159"],"related_works":["https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W4379231730","https://openalex.org/W2265065644","https://openalex.org/W2134699697","https://openalex.org/W2322875716","https://openalex.org/W4324315429","https://openalex.org/W2501551404","https://openalex.org/W2468698815","https://openalex.org/W4385583601"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,34,62,68,88,93,111],"use":[4,48],"of":[5],"Adaptor":[6,41],"Grammars,":[7],"a":[8,28,49,82],"nonparametric":[9],"Bayesian":[10],"modelling":[11],"framework,":[12],"for":[13],"minimally":[14],"supervised":[15],"morphological":[16],"segmentation.":[17],"We":[18,71],"compare":[19],"three":[20],"training":[21,80],"methods:":[22],"unsupervised":[23,40,85],"training,":[24,26,86],"semi-supervised":[25,79,105],"and":[27,76,100],"novel":[29],"model":[30,35,89],"selection":[31,36,90],"method.":[32],"In":[33],"method,":[37],"we":[38],"train":[39],"Grammars":[42],"using":[43],"an":[44],"over-articulated":[45],"metagrammar,":[46],"then":[47],"small":[50],"labelled":[51],"data":[52],"set":[53],"to":[54,113,117],"select":[55],"which":[56],"potential":[57,112],"morph":[58],"boundaries":[59],"identified":[60],"by":[61],"metagrammar":[63],"should":[64],"be":[65],"returned":[66],"in":[67],"final":[69],"output.":[70],"evaluate":[72],"on":[73],"five":[74],"languages":[75,99],"show":[77],"that":[78],"provides":[81,110],"boost":[83],"over":[84,97],"while":[87],"method":[91,109],"yields":[92],"best":[94],"average":[95],"results":[96],"all":[98],"is":[101],"competitive":[102],"with":[103],"state-of-the-art":[104],"systems.":[106],"Moreover,":[107],"this":[108],"tune":[114],"performance":[115],"according":[116],"different":[118],"evaluation":[119],"metrics":[120],"or":[121],"downstream":[122],"tasks.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}