{"id":"https://openalex.org/W2989457779","doi":"https://doi.org/10.18653/v1/k19-1021","title":"On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages","display_name":"On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2989457779","doi":"https://doi.org/10.18653/v1/k19-1021","mag":"2989457779"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k19-1021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1021","pdf_url":null,"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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/k19-1021","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100434324","display_name":"Yi Zhu","orcid":"https://orcid.org/0000-0003-3000-3918"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073408576","display_name":"Benjamin Heinzerling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Heinzerling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014866912","display_name":"Ivan Vuli\u0107","orcid":"https://orcid.org/0000-0002-5161-5422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Vuli\u0107","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020347604","display_name":"Michael Strube","orcid":"https://orcid.org/0000-0002-4731-8142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Strube","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054952724","display_name":"Roi Reichart","orcid":"https://orcid.org/0000-0001-6918-0554"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roi Reichart","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081393566","display_name":"Anna Korhonen","orcid":"https://orcid.org/0000-0002-3692-3144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anna Korhonen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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":0.9948999881744385,"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":0.7909133434295654},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.732933759689331},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7077908515930176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.652229905128479},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6087798476219177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5628587603569031},{"id":"https://openalex.org/keywords/zulu","display_name":"Zulu","score":0.5385820269584656},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5224441885948181},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.4104117155075073},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19532638788223267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7909133434295654},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.732933759689331},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7077908515930176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.652229905128479},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6087798476219177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5628587603569031},{"id":"https://openalex.org/C2778105672","wikidata":"https://www.wikidata.org/wiki/Q10179","display_name":"Zulu","level":2,"score":0.5385820269584656},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5224441885948181},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.4104117155075073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19532638788223267},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/k19-1021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1021","pdf_url":null,"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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/k19-1021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1021","pdf_url":null,"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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1964045210","https://openalex.org/W2064675550","https://openalex.org/W2080133951","https://openalex.org/W2153579005","https://openalex.org/W2167419393","https://openalex.org/W2250618788","https://openalex.org/W2296283641","https://openalex.org/W2406945108","https://openalex.org/W2493916176","https://openalex.org/W2494423583","https://openalex.org/W2570821393","https://openalex.org/W2606342375","https://openalex.org/W2626433756","https://openalex.org/W2741986357","https://openalex.org/W2803214681","https://openalex.org/W2807036468","https://openalex.org/W2810095012","https://openalex.org/W2835793135","https://openalex.org/W2880875857","https://openalex.org/W2890225082","https://openalex.org/W2891680269","https://openalex.org/W2946817437","https://openalex.org/W2954699761","https://openalex.org/W2962685689","https://openalex.org/W2962702662","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963099225","https://openalex.org/W2963206679","https://openalex.org/W2963324947","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963421945","https://openalex.org/W2963667932","https://openalex.org/W2963672540","https://openalex.org/W2963711067","https://openalex.org/W2963979492","https://openalex.org/W2964005834","https://openalex.org/W2964090065","https://openalex.org/W2964121744","https://openalex.org/W2964144280","https://openalex.org/W2964265128","https://openalex.org/W2964302308","https://openalex.org/W2970854433"],"related_works":["https://openalex.org/W1863852300","https://openalex.org/W2121631514","https://openalex.org/W2322995400","https://openalex.org/W421592779","https://openalex.org/W2216379849","https://openalex.org/W2917105808","https://openalex.org/W1982195352","https://openalex.org/W2228493318","https://openalex.org/W2158896293","https://openalex.org/W1700401920"],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2],"validated":[3],"the":[4,43,90,99,135,138,167,175,179,187,194],"importance":[5],"of":[6,45,79,83,92,101,119,137,170,189],"subword":[7],"information":[8],"for":[9,47,56,192],"word":[10,48,107,140],"representation":[11,49,141],"learning.":[12],"Since":[13],"subwords":[14,46,171],"increase":[15],"parameter":[16],"sharing":[17],"ability":[18],"in":[19,29,51],"neural":[20],"models,":[21,198],"their":[22],"value":[23],"should":[24],"be":[25],"even":[26,97],"more":[27,206],"pronounced":[28],"low-data":[30],"regimes.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"therefore":[36],"provide":[37],"a":[38,72,117,205],"comprehensive":[39],"analysis":[40],"focused":[41],"on":[42,174,186],"usefulness":[44],"learning":[50],"truly":[52,126],"low-resource":[53,127],"scenarios":[54],"and":[55,66,132,178,196],"three":[57],"representative":[58],"morphological":[59,64],"tasks:":[60],"fine-grained":[61],"entity":[62,68],"typing,":[63],"tagging,":[65],"named":[67],"recognition.":[69],"We":[70],"conduct":[71],"systematic":[73],"study":[74],"that":[75,147,166],"spans":[76],"several":[77],"dimensions":[78],"comparison:":[80],"1)":[81],"type":[82,113],"data":[84,103,191,203],"scarcity":[85],"which":[86],"can":[87],"stem":[88],"from":[89,98],"lack":[91,100],"task-specific":[93],"training":[94,193],"data,":[95],"or":[96,109],"unannotated":[102],"required":[104],"to":[105],"train":[106],"embeddings,":[108],"both;":[110],"2)":[111],"language":[112,155,176],"by":[114],"working":[115],"with":[116,157],"sample":[118],"16":[120],"typologically":[121],"diverse":[122],"languages":[123],"including":[124],"some":[125],"ones":[128],"(e.g.":[129],"Rusyn,":[130],"Buryat,":[131],"Zulu);":[133],"3)":[134],"choice":[136],"subword-informed":[139,148],"method.":[142],"Our":[143],"main":[144],"results":[145],"show":[146],"models":[149],"are":[150],"universally":[151],"useful":[152],"across":[153],"all":[154],"types,":[156],"large":[158],"gains":[159],"over":[160],"subword-agnostic":[161],"embeddings.":[162],"They":[163],"also":[164],"suggest":[165],"effective":[168],"use":[169],"largely":[172],"depends":[173],"(type)":[177],"task":[180],"at":[181],"hand,":[182],"as":[183,185],"well":[184],"amount":[188],"available":[190],"embeddings":[195],"task-based":[197],"where":[199],"having":[200],"sufficient":[201],"in-task":[202],"is":[204],"critical":[207],"requirement.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}