{"id":"https://openalex.org/W2883158411","doi":"https://doi.org/10.1162/tacl_a_00032","title":"Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction","display_name":"Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2883158411","doi":"https://doi.org/10.1162/tacl_a_00032","mag":"2883158411"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00032","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00032","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00032","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","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078083355","display_name":"Daniela Gerz","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Daniela Gerz","raw_affiliation_strings":["Language Technology Lab, DTAL, University of Cambridge,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Lab, DTAL, University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014866912","display_name":"Ivan Vuli\u0107","orcid":"https://orcid.org/0000-0002-5161-5422"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ivan Vuli\u0107","raw_affiliation_strings":["Language Technology Lab, DTAL, University of Cambridge,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Lab, DTAL, University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014613113","display_name":"Edoardo Maria Ponti","orcid":"https://orcid.org/0000-0002-6308-1050"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Edoardo Ponti","raw_affiliation_strings":["Language Technology Lab, DTAL, University of Cambridge,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Lab, DTAL, University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082047528","display_name":"Jason Naradowsky","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason Naradowsky","raw_affiliation_strings":["Johns Hopkins University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054952724","display_name":"Roi Reichart","orcid":"https://orcid.org/0000-0001-6918-0554"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Roi Reichart","raw_affiliation_strings":["Faculty of Industrial Engineering and Management, Technion, IIT,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Industrial Engineering and Management, Technion, IIT,","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081393566","display_name":"Anna Korhonen","orcid":"https://orcid.org/0000-0002-3692-3144"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Anna Korhonen","raw_affiliation_strings":["Language Technology Lab, DTAL, University of Cambridge,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Lab, DTAL, University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014613113","https://openalex.org/A5014866912","https://openalex.org/A5054952724","https://openalex.org/A5078083355","https://openalex.org/A5081393566","https://openalex.org/A5082047528"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I174306211","https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":6.2698,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97036825,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"6","issue":null,"first_page":"451","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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/perplexity","display_name":"Perplexity","score":0.9116212129592896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8904123306274414},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7141534686088562},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6990431547164917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6945463418960571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6330778002738953},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6268523335456848},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5576488971710205},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5249474048614502},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4445386230945587},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15126639604568481},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10884362459182739}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9116212129592896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8904123306274414},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7141534686088562},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6990431547164917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6945463418960571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6330778002738953},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6268523335456848},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5576488971710205},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5249474048614502},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4445386230945587},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15126639604568481},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10884362459182739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/tacl_a_00032","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00032","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00032","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:pure.ed.ac.uk:publications/42add9a4-26ad-48ee-b5e2-16108f93ef8d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/42add9a4-26ad-48ee-b5e2-16108f93ef8d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Gerz, D, Vuli\u0107, I, Ponti, E, Naradowsky, J, Reichart, R & Korhonen, A 2018, 'Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction', Transactions of the Association for Computational Linguistics, vol. 6, pp. 451-465. https://doi.org/10.1162/tacl_a_00032","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:968c7798c0f04da68341f24cc6fd6fb9","is_oa":false,"landing_page_url":"https://doaj.org/article/968c7798c0f04da68341f24cc6fd6fb9","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 6 (2021)","raw_type":"article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/279936","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/279936","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":null,"raw_type":"Article"},{"id":"doi:10.17863/cam.27304","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.27304","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00032","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00032","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00032","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":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2883158411.pdf","grobid_xml":"https://content.openalex.org/works/W2883158411.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W179875071","https://openalex.org/W630532510","https://openalex.org/W932413789","https://openalex.org/W1503259811","https://openalex.org/W1505680913","https://openalex.org/W1517590677","https://openalex.org/W1591801644","https://openalex.org/W1632114991","https://openalex.org/W1665214252","https://openalex.org/W1810943226","https://openalex.org/W1814992895","https://openalex.org/W1849277567","https://openalex.org/W1899794420","https://openalex.org/W1934041838","https://openalex.org/W1938755728","https://openalex.org/W1985258458","https://openalex.org/W2038721957","https://openalex.org/W2041258965","https://openalex.org/W2064675550","https://openalex.org/W2111305191","https://openalex.org/W2113459411","https://openalex.org/W2129250947","https://openalex.org/W2146502635","https://openalex.org/W2154579312","https://openalex.org/W2159746348","https://openalex.org/W2168664213","https://openalex.org/W2251044566","https://openalex.org/W2251654079","https://openalex.org/W2259472270","https://openalex.org/W2270190199","https://openalex.org/W2271840356","https://openalex.org/W2321470647","https://openalex.org/W2401969231","https://openalex.org/W2507731975","https://openalex.org/W2508661145","https://openalex.org/W2591264712","https://openalex.org/W2611669587","https://openalex.org/W2620558438","https://openalex.org/W2741986357","https://openalex.org/W2949563612","https://openalex.org/W2962883855","https://openalex.org/W2963099225","https://openalex.org/W2963173190","https://openalex.org/W2963216505","https://openalex.org/W2963324947","https://openalex.org/W2963347649","https://openalex.org/W2963582782","https://openalex.org/W2963899393","https://openalex.org/W2963901637","https://openalex.org/W2964318358","https://openalex.org/W3038058348","https://openalex.org/W4205167092","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2921174581","https://openalex.org/W2084531783","https://openalex.org/W2020757772"],"abstract_inverted_index":{"Neural":[0],"architectures":[1],"are":[2,179],"prominent":[3],"in":[4,62,149],"the":[5,53,110,137,150,154],"construction":[6],"of":[7,17,31,45,55,101,120,156],"language":[8,63,139],"models":[9,39,57,69],"(LMs).":[10],"However,":[11],"word-level":[12,144],"prediction":[13,61],"is":[14,123,159],"typically":[15],"agnostic":[16],"subword-level":[18,67,114,129],"information":[19,130],"(characters":[20],"and":[21,24,104,161,176],"character":[22],"sequences)":[23],"operates":[25],"over":[26],"a":[27,32,43,88,98,124],"closed":[28],"vocabulary,":[29],"consisting":[30],"limited":[33],"word":[34,133],"set.":[35],"Indeed,":[36],"while":[37,112],"subword-aware":[38],"boost":[40],"performance":[41],"across":[42,166],"variety":[44,100],"NLP":[46],"tasks,":[47],"previous":[48],"work":[49,122],"did":[50],"not":[51],"evaluate":[52],"ability":[54],"these":[56],"to":[58,109,142],"assist":[59],"next-word":[60],"modeling":[64,140],"tasks.":[65],"Such":[66],"informed":[68],"should":[70],"be":[71],"particularly":[72],"effective":[73],"for":[74,127,171],"morphologically-rich":[75,172],"languages":[76,96],"(MRLs)":[77],"that":[78],"exhibit":[79],"high":[80],"type-to-token":[81],"ratios.":[82],"In":[83],"this":[84],"work,":[85],"we":[86],"present":[87],"large-scale":[89],"LM":[90,107,151],"study":[91],"on":[92],"50":[93,168],"typologically":[94],"diverse":[95],"covering":[97],"wide":[99],"morphological":[102],"systems,":[103],"offer":[105],"new":[106],"benchmarks":[108],"community,":[111],"considering":[113],"information.":[115],"The":[116],"main":[117],"technical":[118],"contribution":[119],"our":[121,167],"novel":[125],"method":[126],"injecting":[128],"into":[131,136],"semantic":[132],"vectors,":[134],"integrated":[135],"neural":[138],"training,":[141],"facilitate":[143],"prediction.":[145],"We":[146],"conduct":[147],"experiments":[148],"setting":[152],"where":[153],"number":[155],"infrequent":[157],"words":[158],"large,":[160],"demonstrate":[162],"strong":[163],"perplexity":[164],"gains":[165],"languages,":[169],"especially":[170],"languages.":[173],"Our":[174],"code":[175],"data":[177],"sets":[178],"publicly":[180],"available.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-10-10T00:00:00"}