{"id":"https://openalex.org/W4403795660","doi":"https://doi.org/10.48550/arxiv.2409.17373","title":"data2lang2vec: Data Driven Typological Features Completion","display_name":"data2lang2vec: Data Driven Typological Features Completion","publication_year":2024,"publication_date":"2024-09-25","ids":{"openalex":"https://openalex.org/W4403795660","doi":"https://doi.org/10.48550/arxiv.2409.17373"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.17373","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.17373","pdf_url":"https://arxiv.org/pdf/2409.17373","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.17373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092810082","display_name":"Hamidreza Amirzadeh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]},{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK","IR"],"is_corresponding":false,"raw_author_name":"Amirzadeh, Hamidreza","raw_affiliation_strings":["IT University of Copenhagen , Denmark","Sharif University of Technology , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen , Denmark","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"Sharif University of Technology , Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jafari, Sadegh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]},{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK","IR"],"is_corresponding":false,"raw_author_name":"Jafari, Sadegh","raw_affiliation_strings":["IT University of Copenhagen , Denmark","Iran University of Science and Technology , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen , Denmark","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"Iran University of Science and Technology , Iran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114418775","display_name":"Anika Harju","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Harju, Anika","raw_affiliation_strings":["IT University of Copenhagen , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen , Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039811894","display_name":"Rob van der Goot","orcid":"https://orcid.org/0009-0003-1999-4156","observed_orcids":["https://orcid.org/0009-0003-1999-4156"]},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"van der Goot, Rob","raw_affiliation_strings":["IT University of Copenhagen , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen , Denmark","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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":0.0012000000569969416,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/linguistic-typology","display_name":"linguistic typology","score":0.906000018119812},{"id":"https://openalex.org/keywords/multilingual-nlp","display_name":"multilingual NLP","score":0.6320000290870667}],"concepts":[{"id":"https://openalex.org/C2779538338","wikidata":"https://www.wikidata.org/wiki/Q2990590","display_name":"Completion (oil and gas wells)","level":2,"score":0.505186140537262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.474477082490921},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3467605412006378},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3353651165962219},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.3224793076515198},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.12555378675460815},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2409.17373","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.17373","pdf_url":"https://arxiv.org/pdf/2409.17373","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:archive.ugent.be:01KGF2RRQJQZ2VG4XWGPG9GK0J","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1854/LU-01KGF2RRQJQZ2VG4XWGPG9GK0J","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9798891761964","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.atira.dk:openaire/64bc135f-7034-4191-b5c6-975ba3c36db0","doi":null,"is_oa":true,"landing_page_url":"https://aclanthology.org/2025.coling-main.435/","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2409.17373","doi":"https://doi.org/10.48550/arxiv.2409.17373","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.17373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.17373","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.17373","pdf_url":"https://arxiv.org/pdf/2409.17373","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403795660.pdf","grobid_xml":"https://content.openalex.org/works/W4403795660.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2956037227","https://openalex.org/W3023706255","https://openalex.org/W4388834668","https://openalex.org/W6941014776","https://openalex.org/W7208706621","https://openalex.org/W7203943637","https://openalex.org/W4411638674","https://openalex.org/W7011771313","https://openalex.org/W3022495033","https://openalex.org/W2890225082"],"abstract_inverted_index":{"Language":[0,6],"typology":[1,106],"databases":[2],"enhance":[3],"multi-lingual":[4,68],"Natural":[5],"Processing":[7],"(NLP)":[8],"by":[9],"improving":[10],"model":[11],"adaptability":[12],"to":[13,54,103],"diverse":[14],"linguistic":[15],"structures.":[16],"The":[17],"widely-used":[18],"lang2vec":[19],"toolkit":[20],"integrates":[21],"several":[22],"such":[23],"databases,":[24],"but":[25],"its":[26],"coverage":[27,37],"remains":[28],"limited":[29],"at":[30],"28.9\\%.":[31],"Previous":[32],"work":[33,115],"on":[34,42,49,101],"automatically":[35],"increasing":[36],"predicts":[38],"missing":[39,105],"values":[40],"based":[41],"features":[43,84],"from":[44],"other":[45],"languages":[46],"or":[47],"focuses":[48],"single":[50],"features,":[51,107],"we":[52,65],"propose":[53],"use":[55],"textual":[56],"data":[57],"for":[58],"better-informed":[59],"feature":[60],"prediction.":[61],"To":[62],"this":[63],"end,":[64],"introduce":[66,94],"a":[67,86,95],"Part-of-Speech":[69],"(POS)":[70],"tagger,":[71],"achieving":[72],"over":[73],"70\\%":[74],"accuracy":[75],"across":[76],"1,749":[77],"languages,":[78],"and":[79,85,108],"experiment":[80],"with":[81],"external":[82],"statistical":[83],"variety":[87],"of":[88],"machine":[89],"learning":[90],"algorithms.":[91],"We":[92],"also":[93],"more":[96],"realistic":[97],"evaluation":[98],"setup,":[99],"focusing":[100],"likely":[102],"be":[104],"show":[109],"that":[110],"our":[111],"approach":[112],"outperforms":[113],"previous":[114],"in":[116],"both":[117],"setups.":[118]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2024-10-27T00:00:00"}
