{"id":"https://openalex.org/W4416037907","doi":"https://doi.org/10.18653/v1/2025.emnlp-demos.23","title":"DistaLs: a Comprehensive Collection of Language Distance Measures","display_name":"DistaLs: a Comprehensive Collection of Language Distance Measures","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037907","doi":"https://doi.org/10.18653/v1/2025.emnlp-demos.23"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.emnlp-demos.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-demos.23","pdf_url":"https://aclanthology.org/2025.emnlp-demos.23.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 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-demos.23.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039811894","display_name":"Rob van der Goot","orcid":"https://orcid.org/0009-0003-1999-4156"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rob Van Der Goot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043100830","display_name":"Esther Ploeger","orcid":"https://orcid.org/0009-0007-9525-3359"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Esther Ploeger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007661580","display_name":"Verena Blaschke","orcid":"https://orcid.org/0000-0002-1082-2740"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Verena Blaschke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017310324","display_name":"Tanja Samard\u017ci\u0107","orcid":"https://orcid.org/0000-0001-6451-3946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanja Samardzic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.16031156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"307","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.54339998960495,"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":0.54339998960495,"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/T12090","display_name":"Language and cultural evolution","score":0.25870001316070557,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.07540000230073929,"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/variety","display_name":"Variety (cybernetics)","score":0.7685999870300293},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.579800009727478},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.413100004196167},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.37940001487731934},{"id":"https://openalex.org/keywords/distance-measures","display_name":"Distance measures","score":0.31029999256134033},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.2888999879360199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829999923706055},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7685999870300293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6157000064849854},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5681999921798706},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.27079999446868896}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-demos.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-demos.23","pdf_url":"https://aclanthology.org/2025.emnlp-demos.23.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 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/1c7b8ccc-fa02-4b8f-914b-39029c09d1bb","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/1c7b8ccc-fa02-4b8f-914b-39029c09d1bb","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"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":"Goot, R V D, Ploeger, E, Blaschke, V & Samardzic, T 2025, DistaLs: a Comprehensive Collection of Language Distance Measures. in I Habernal, P Schulam & J Tiedemann (eds), Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Suzhou, China, pp. 307-318, Conference on Empirical Methods in Natural Language Processing, Suzhou, China, 04/11/2025. https://doi.org/10.18653/v1/2025.emnlp-demos.23","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:openaire/d90332de-84db-46a6-8170-74324b80e021","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/d90332de-84db-46a6-8170-74324b80e021","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"van der Goot, R, Ploeger, E, Blaschke, V & Samard\u017ei\u0107, T 2025, DistaLs : a Comprehensive Collection of Language Distance Measures. in I Habernal , P Schulam & J Tiedemann (eds), Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing : System Demonstrations. Association for Computational Linguistics, pp. 307-318, 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Suzhou, China, 04/11/2025. https://doi.org/10.18653/v1/2025.emnlp-demos.23","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-demos.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-demos.23","pdf_url":"https://aclanthology.org/2025.emnlp-demos.23.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 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037907.pdf","grobid_xml":"https://content.openalex.org/works/W4416037907.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Languages":[0],"vary":[1],"along":[2],"a":[3,72,85,97,106,123,130,142,147],"wide":[4,98],"variety":[5,99,124],"of":[6,75,100,125,157],"dimensions.In":[7],"Natural":[8],"Language":[9],"Processing":[10],"(NLP),":[11],"it":[12,39],"is":[13,88,117,136],"useful":[14],"to":[15,90,96,119,154],"know":[16],"how":[17,44,55],"\"distant\"":[18],"languages":[19,58],"are":[20,50],"from":[21],"each":[22],"other,":[23],"so":[24],"that":[25,87],"we":[26,82,145,151],"can":[27,40],"inform":[28,41],"NLP":[29],"models":[30],"about":[31,43],"these":[32],"differences":[33],"or":[34,71,79],"predict":[35],"good":[36],"transfer":[37],"languages.Furthermore,":[38],"us":[42],"diverse":[45],"language":[46,101],"samples":[47],"are.However,":[48],"there":[49],"many":[51],"different":[52,164],"perspectives":[53],"on":[54,68,162],"distances":[56],"across":[57],"could":[59],"be":[60,120],"measured,":[61],"and":[62,113,128,133,139],"previous":[63],"work":[64],"has":[65],"predominantly":[66],"focused":[67],"either":[69],"intuition":[70],"single":[73],"type":[74],"distance,":[76],"like":[77],"genealogical":[78],"typological":[80],"distance.Therefore,":[81],"propose":[83,105],"DistaLs,":[84],"toolkit":[86],"designed":[89,118],"provide":[91,146],"users":[92],"with":[93,160],"easy":[94],"access":[95],"distance":[102,158],"measures.We":[103],"also":[104],"filtered":[107],"subset,":[108],"which":[109,150],"contains":[110],"less":[111],"redundant":[112],"more":[114],"reliable":[115],"features.DistaLs":[116],"accessible":[121],"for":[122],"use":[126,152],"cases,":[127],"offers":[129],"Python,":[131],"CLI,":[132],"web":[134],"interface.It":[135],"easily":[137],"updateable,":[138],"available":[140],"as":[141],"pip":[143],"package.Finally,":[144],"case-study":[148],"in":[149],"DistaLs":[153],"measure":[155],"correlations":[156],"measures":[159],"performance":[161],"four":[163],"morphosyntactic":[165],"tasks.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}