{"id":"https://openalex.org/W7140078307","doi":"https://doi.org/10.18653/v1/2026.eacl-srw.19","title":"Trainable, Multiword-aware Linguistic Tokenization Using Modern Neural Networks","display_name":"Trainable, Multiword-aware Linguistic Tokenization Using Modern Neural Networks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140078307","doi":"https://doi.org/10.18653/v1/2026.eacl-srw.19"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-srw.19","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-srw.19","pdf_url":"https://aclanthology.org/2026.eacl-srw.19.pdf","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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-srw.19.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130343654","display_name":"Clara Boesenberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clara Boesenberg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052327595","display_name":"Kilian Evang","orcid":null},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kilian Evang","raw_affiliation_strings":["Institute of Linguistics Heinrich Heine University D\u00fcsseldorf"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Linguistics Heinrich Heine University D\u00fcsseldorf","institution_ids":["https://openalex.org/I44260953"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23538157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.4377000033855438,"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":0.4377000033855438,"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":0.18780000507831573,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.024800000712275505,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.5029000043869019},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.33660000562667847},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3337000012397766},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.24719999730587006},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.24459999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.645799994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299999713897705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.45329999923706055},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.24719999730587006},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.24459999799728394},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2395000010728836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-srw.19","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-srw.19","pdf_url":"https://aclanthology.org/2026.eacl-srw.19.pdf","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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-srw.19","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-srw.19","pdf_url":"https://aclanthology.org/2026.eacl-srw.19.pdf","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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4159974753856659}],"awards":[{"id":"https://openalex.org/G4386810966","display_name":"Mehrwortausdr\u00fccke im syntaktischen und semantischen Parsing","funder_award_id":"467699802","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140078307.pdf","grobid_xml":"https://content.openalex.org/works/W7140078307.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"revisit":[1],"MWE-aware":[2,96],"linguistic":[3,28],"tokenization":[4],"as":[5,33,54],"a":[6,15,26,34,37,106],"character-level":[7,38],"and":[8,13,22,42,98,108],"token-level":[9,55],"sequence":[10],"labeling":[11],"problem":[12],"present":[14],"systematic":[16],"evaluation":[17],"on":[18,49,57],"English,":[19],"German,":[20],"Italian,":[21],"Dutch":[23],"data.We":[24],"compare":[25],"standard":[27],"tokenizer":[29],"trained":[30,46],"without":[31],"MWE-awareness":[32],"baseline":[35],"(UDPipe),":[36],"SRN+CRF":[39],"model":[40],"(Elephant),":[41],"transformerbased":[43],"MaChAmp":[44,71],"models":[45],"either":[47],"directly":[48],"gold":[50],"character":[51],"labels":[52],"or":[53],"postprocessors":[56],"top":[58],"of":[59,79],"UDPipe.Our":[60],"results":[61],"show":[62],"that":[63,100],"the":[64,75],"two-stage":[65],"pipeline":[66],"-UDPipe":[67],"pretokenization":[68],"followed":[69],"by":[70],"postprocessing":[72,101],"-consistently":[73],"yields":[74],"best":[76],"accuracy.Our":[77],"analysis":[78],"error":[80],"patterns":[81],"highlights":[82],"how":[83],"different":[84],"architectures":[85],"trade":[86],"off":[87],"over-and":[88],"undersegmentation.These":[89],"findings":[90],"provide":[91],"practical":[92],"guidance":[93],"for":[94,111],"building":[95],"tokenizers":[97],"suggest":[99],"pipelines":[102],"with":[103],"transformers":[104],"are":[105],"strong":[107],"general":[109],"strategy":[110],"non-standard":[112],"tokenization.":[113]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-03-24T00:00:00"}