{"id":"https://openalex.org/W2804033347","doi":"https://doi.org/10.1162/tacl_a_00033","title":"Universal Word Segmentation: Implementation and Interpretation","display_name":"Universal Word Segmentation: Implementation and Interpretation","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2804033347","doi":"https://doi.org/10.1162/tacl_a_00033","mag":"2804033347"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00033","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00033","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00033","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_00033","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080934091","display_name":"Yan Shao","orcid":"https://orcid.org/0009-0001-1130-9201"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Yan Shao","raw_affiliation_strings":["Department of Linguistics and Philology, Uppsala University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics and Philology, Uppsala University,","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042862432","display_name":"Christian Hardmeier","orcid":"https://orcid.org/0000-0002-6103-7275"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Christian Hardmeier","raw_affiliation_strings":["Department of Linguistics and Philology, Uppsala University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics and Philology, Uppsala University,","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077063699","display_name":"Joakim Nivre","orcid":null},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Joakim Nivre","raw_affiliation_strings":["Department of Linguistics and Philology, Uppsala University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics and Philology, Uppsala University,","institution_ids":["https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5042862432","https://openalex.org/A5077063699","https://openalex.org/A5080934091"],"corresponding_institution_ids":["https://openalex.org/I123387679"],"apc_list":null,"apc_paid":null,"fwci":4.0572,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94780824,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"421","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9905999898910522,"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":0.9817000031471252,"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":0.8543736934661865},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.805321991443634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7501773834228516},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.7268355488777161},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.711135745048523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5904404520988464},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5500756502151489},{"id":"https://openalex.org/keywords/hebrew","display_name":"Hebrew","score":0.4863877594470978},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46107980608940125},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.43586379289627075},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4331579804420471},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4294899106025696},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21748891472816467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543736934661865},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.805321991443634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7501773834228516},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.7268355488777161},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.711135745048523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904404520988464},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5500756502151489},{"id":"https://openalex.org/C91304198","wikidata":"https://www.wikidata.org/wiki/Q9288","display_name":"Hebrew","level":2,"score":0.4863877594470978},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46107980608940125},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.43586379289627075},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4331579804420471},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4294899106025696},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21748891472816467},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/tacl_a_00033","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00033","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00033","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:openaire/e4adcca0-c587-4c12-a75b-4b84f5589bd1","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/e4adcca0-c587-4c12-a75b-4b84f5589bd1","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":"Shao, Y, Hardmeier, C & Nivre, J 2018, 'Universal Word Segmentation: Implementation and Interpretation', Transactions of the Association for Computational Linguistics, vol. 6, pp. 421-435. https://doi.org/10.1162/tacl_a_00033","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:DiVA.org:uu-348128","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-348128","pdf_url":null,"source":{"id":"https://openalex.org/S4306400653","display_name":"Diva portal (Dalarna University Library)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:1c764ccc407c4f8c8dbd44d6484cd5dc","is_oa":false,"landing_page_url":"https://doaj.org/article/1c764ccc407c4f8c8dbd44d6484cd5dc","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:pure.ed.ac.uk:publications/e4adcca0-c587-4c12-a75b-4b84f5589bd1","is_oa":true,"landing_page_url":"https://www-ed.elsevierpure.com/en/publications/e4adcca0-c587-4c12-a75b-4b84f5589bd1","pdf_url":null,"source":null,"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:10.1162/tacl_a_00033","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00033","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00033","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":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2804033347.pdf","grobid_xml":"https://content.openalex.org/works/W2804033347.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W117637812","https://openalex.org/W1218353304","https://openalex.org/W1498763386","https://openalex.org/W1533861849","https://openalex.org/W1940872118","https://openalex.org/W2046033161","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2106657366","https://openalex.org/W2128728535","https://openalex.org/W2128862864","https://openalex.org/W2146502635","https://openalex.org/W2147880316","https://openalex.org/W2155974709","https://openalex.org/W2163377725","https://openalex.org/W2250659129","https://openalex.org/W2250739653","https://openalex.org/W2251670681","https://openalex.org/W2739776664","https://openalex.org/W2739827909","https://openalex.org/W2740838408","https://openalex.org/W2741029840","https://openalex.org/W2807107383","https://openalex.org/W2952054097","https://openalex.org/W2953320089","https://openalex.org/W2953384591","https://openalex.org/W2964199361","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2891418498","https://openalex.org/W2900287580","https://openalex.org/W2807934979","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2785359773"],"abstract_inverted_index":{"Word":[0],"segmentation":[1,30,55,62,96],"is":[2,8,64],"a":[3,11,21,32,86],"low-level":[4],"NLP":[5],"task":[6],"that":[7,61,119],"non-trivial":[9,121],"for":[10,31],"considerable":[12],"number":[13,75],"of":[14,35,76,89],"languages.":[15,112],"In":[16],"this":[17],"paper,":[18],"we":[19,45,84],"present":[20],"sequence":[22],"tagging":[23],"framework":[24],"and":[25,41,53,71,92,129],"apply":[26],"it":[27],"to":[28,67,73,122,133],"word":[29,54,68],"wide":[33],"range":[34],"languages":[36,118],"with":[37],"different":[38],"writing":[39],"systems":[40],"typological":[42,51],"characteristics.":[43],"Additionally,":[44],"investigate":[46],"the":[47,74,82,95,99,110],"correlations":[48],"between":[49],"various":[50],"factors":[52],"accuracy.":[56],"The":[57],"experimental":[58],"results":[59],"indicate":[60],"accuracy":[63],"positively":[65],"related":[66],"boundary":[69],"markers":[70],"negatively":[72],"unique":[77],"non-segmental":[78],"terms.":[79],"Based":[80],"on":[81,98,108,117],"analysis,":[83],"design":[85],"small":[87],"set":[88],"language-specific":[90],"settings":[91],"extensively":[93],"evaluate":[94],"system":[97],"Universal":[100],"Dependencies":[101],"datasets.":[102],"Our":[103],"model":[104],"obtains":[105],"state-of-the-art":[106],"accuracies":[107],"all":[109],"UD":[111],"It":[113],"performs":[114],"substantially":[115],"better":[116],"are":[120],"segment,":[123],"such":[124],"as":[125],"Chinese,":[126],"Japanese,":[127],"Arabic":[128],"Hebrew,":[130],"when":[131],"compared":[132],"previous":[134],"work.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}