{"id":"https://openalex.org/W2805083960","doi":"https://doi.org/10.1162/coli_a_00325","title":"Using Semantics for Granularities of Tokenization","display_name":"Using Semantics for Granularities of Tokenization","publication_year":2018,"publication_date":"2018-06-07","ids":{"openalex":"https://openalex.org/W2805083960","doi":"https://doi.org/10.1162/coli_a_00325","mag":"2805083960"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00325","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00325","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00325","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00325","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035714052","display_name":"Martin Riedl","orcid":"https://orcid.org/0000-0003-2411-1998"},"institutions":[{"id":"https://openalex.org/I4210088543","display_name":"Institut f\u00fcr Informationsverarbeitung","ror":"https://ror.org/0047j9t38","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210088543"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin Riedl","raw_affiliation_strings":["University of Stuttgart, Institut f\u00fcr maschinelle Sprachverarbeitung"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institut f\u00fcr maschinelle Sprachverarbeitung","institution_ids":["https://openalex.org/I4210088543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Chris Biemann","raw_affiliation_strings":["University of Hamburg, Language Technology Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hamburg, Language Technology Group","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021287757","https://openalex.org/A5035714052"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I4210088543","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":0.8468,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80111602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"44","issue":"3","first_page":"483","last_page":"524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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":0.8818280696868896},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7145424485206604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.685082197189331},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6067187190055847},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5932492017745972},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5416394472122192},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5077625513076782},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.500044584274292},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49527159333229065},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.43360012769699097},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4315912127494812},{"id":"https://openalex.org/keywords/stop-words","display_name":"Stop words","score":0.42265379428863525},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4210270643234253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8818280696868896},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7145424485206604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.685082197189331},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6067187190055847},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5932492017745972},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5416394472122192},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5077625513076782},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.500044584274292},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49527159333229065},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.43360012769699097},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4315912127494812},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.42265379428863525},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4210270643234253},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00325","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00325","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00325","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f739e90bb4a24f6794543bcd4b417072","is_oa":true,"landing_page_url":"https://doaj.org/article/f739e90bb4a24f6794543bcd4b417072","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 44, Iss 3, Pp 483-524 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00325","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00325","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00325","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2805083960.pdf","grobid_xml":"https://content.openalex.org/works/W2805083960.grobid-xml"},"referenced_works_count":82,"referenced_works":["https://openalex.org/W27310688","https://openalex.org/W99580251","https://openalex.org/W144264647","https://openalex.org/W153318553","https://openalex.org/W174126432","https://openalex.org/W1498763386","https://openalex.org/W1508106516","https://openalex.org/W1516184288","https://openalex.org/W1535206496","https://openalex.org/W1537288903","https://openalex.org/W1543444773","https://openalex.org/W1574901103","https://openalex.org/W1576685422","https://openalex.org/W1587989021","https://openalex.org/W1595595359","https://openalex.org/W1607035479","https://openalex.org/W1743573446","https://openalex.org/W1875999651","https://openalex.org/W1956785191","https://openalex.org/W1970607377","https://openalex.org/W1995905884","https://openalex.org/W2016856586","https://openalex.org/W2031203571","https://openalex.org/W2032039936","https://openalex.org/W2037450062","https://openalex.org/W2042380438","https://openalex.org/W2044070623","https://openalex.org/W2044374589","https://openalex.org/W2046045616","https://openalex.org/W2051840908","https://openalex.org/W2061556378","https://openalex.org/W2074228526","https://openalex.org/W2093418984","https://openalex.org/W2123084125","https://openalex.org/W2123489126","https://openalex.org/W2129706127","https://openalex.org/W2134913565","https://openalex.org/W2135891920","https://openalex.org/W2142074148","https://openalex.org/W2143391265","https://openalex.org/W2143670291","https://openalex.org/W2146351783","https://openalex.org/W2153225069","https://openalex.org/W2155512447","https://openalex.org/W2163107094","https://openalex.org/W2163353449","https://openalex.org/W2163953154","https://openalex.org/W2166776180","https://openalex.org/W2168820179","https://openalex.org/W2250250534","https://openalex.org/W2250383887","https://openalex.org/W2250395065","https://openalex.org/W2250452161","https://openalex.org/W2250574900","https://openalex.org/W2251195978","https://openalex.org/W2251400472","https://openalex.org/W2251452258","https://openalex.org/W2251771443","https://openalex.org/W2252211741","https://openalex.org/W2315366077","https://openalex.org/W2338741179","https://openalex.org/W2398936787","https://openalex.org/W2400878268","https://openalex.org/W2463188703","https://openalex.org/W2463932830","https://openalex.org/W2468765526","https://openalex.org/W2547599276","https://openalex.org/W2574418684","https://openalex.org/W2577572530","https://openalex.org/W2612649659","https://openalex.org/W2617339792","https://openalex.org/W2723068199","https://openalex.org/W2785725206","https://openalex.org/W2787482452","https://openalex.org/W2887428522","https://openalex.org/W2911828240","https://openalex.org/W2913252902","https://openalex.org/W2950577311","https://openalex.org/W3089145770","https://openalex.org/W4235019020","https://openalex.org/W4255198209","https://openalex.org/W4404778218"],"related_works":["https://openalex.org/W4298195702","https://openalex.org/W4313403876","https://openalex.org/W1177522693","https://openalex.org/W3093768914","https://openalex.org/W2945402993","https://openalex.org/W3185916216","https://openalex.org/W3000733727","https://openalex.org/W4225939240","https://openalex.org/W4313188041","https://openalex.org/W3010329803"],"abstract_inverted_index":{"Depending":[0],"on":[1,77,85,117,168],"downstream":[2],"applications,":[3],"it":[4],"is":[5,75,109],"advisable":[6],"to":[7,19,243],"extend":[8],"the":[9,78,179,190,219,229,241],"notion":[10],"of":[11,21,33,72,88,158,181,192,246],"tokenization":[12,251],"from":[13,172],"low-level":[14],"character-based":[15],"token":[16],"boundary":[17],"detection":[18,245],"identification":[20],"meaningful":[22,54],"and":[23,62,97,124,167,195,207,228],"useful":[24],"language":[25],"units.":[26],"This":[27],"entails":[28],"both":[29,205],"identifying":[30],"units":[31,248],"composed":[32],"several":[34,40],"single":[35,41],"words":[36,42],"that":[37,43,80,134],"form":[38,44],"a":[39,94,98,110,199,233],"a,":[45],"as":[46,48,258],"well":[47],"splitting":[49],"single-word":[50],"compounds":[51],"into":[52],"their":[53],"parts.":[55],"In":[56,155,198],"this":[57],"article,":[58],"we":[59,90,105,146,177,202,217],"introduce":[60,106],"unsupervised":[61,185],"knowledge-free":[63],"methods":[64,81,140],"for":[65,112,130,151,174],"these":[66],"two":[67,92,122],"tasks.":[68],"The":[69,115],"main":[70],"novelty":[71],"our":[73,182,238],"research":[74],"based":[76,84],"fact":[79],"are":[82],"primarily":[83],"distributional":[86,101,143],"similarity,":[87],"which":[89,108],"use":[91],"flavors:":[93],"sparse":[95],"count-based":[96],"dense":[99],"neural-based":[100],"semantic":[102],"model.":[103],"First,":[104],"DRUID,":[107],"method":[111],"detecting":[113],"MWEs.":[114],"evaluation":[116,127,157],"MWE-annotated":[118],"data":[119,128,162,169],"sets":[120,129,163,170],"in":[121,213,232],"languages":[123,132,166],"newly":[125],"extracted":[126,171],"32":[131],"shows":[133],"DRUID":[135],"compares":[136],"favorably":[137],"over":[138,184],"previous":[139,193],"not":[141],"utilizing":[142],"information.":[144],"Second,":[145],"present":[147],"SECOS,":[148],"an":[149,156],"algorithm":[150],"decompounding":[152,161,206],"close":[153],"compounds.":[154],"four":[159,165],"dedicated":[160],"across":[164],"Wiktionary":[173],"14":[175],"languages,":[176],"demonstrate":[178],"superiority":[180],"approach":[183],"baselines,":[186],"sometimes":[187],"even":[188],"matching":[189],"performance":[191],"language-specific":[194,254],"supervised":[196],"methods.":[197],"final":[200],"experiment,":[201],"show":[203],"how":[204],"MWE":[208],"information":[209,214,225],"can":[210],"be":[211],"used":[212],"retrieval.":[215],"Here,":[216],"obtain":[218],"best":[220],"results":[221],"when":[222],"combining":[223],"word":[224],"with":[226],"MWEs":[227],"compound":[230],"parts":[231],"bag-of-words":[234],"retrieval":[235],"set-up.":[236],"Overall,":[237],"methodology":[239],"paves":[240],"way":[242],"automatic":[244],"lexical":[247],"beyond":[249],"standard":[250],"techniques":[252],"without":[253],"preprocessing":[255],"steps":[256],"such":[257],"POS":[259],"tagging.":[260]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}