{"id":"https://openalex.org/W7126024473","doi":"https://doi.org/10.1109/comcomap68359.2025.11353184","title":"Towards Effective Data Process Pipelines for Legal NLP in English and Non-English Languages: A Greek Case Study","display_name":"Towards Effective Data Process Pipelines for Legal NLP in English and Non-English Languages: A Greek Case Study","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7126024473","doi":"https://doi.org/10.1109/comcomap68359.2025.11353184"},"language":null,"primary_location":{"id":"doi:10.1109/comcomap68359.2025.11353184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comcomap68359.2025.11353184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Computing, Communications and IoT Applications (ComComAp)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048269612","display_name":"Asimina Dimara","orcid":"https://orcid.org/0000-0001-9372-7070"},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Asimina Dimara","raw_affiliation_strings":["University of the Aegean,I-Lab,Dpt. of Cultural Technology & Communication,Mytilene,Greece,81100"],"affiliations":[{"raw_affiliation_string":"University of the Aegean,I-Lab,Dpt. of Cultural Technology & Communication,Mytilene,Greece,81100","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026253993","display_name":"Konstantinos Kotis","orcid":"https://orcid.org/0000-0001-7838-9691"},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Kotis","raw_affiliation_strings":["University of the Aegean,I-Lab,Dpt. of Cultural Technology & Communication,Mytilene,Greece,81100"],"affiliations":[{"raw_affiliation_string":"University of the Aegean,I-Lab,Dpt. of Cultural Technology & Communication,Mytilene,Greece,81100","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050728306","display_name":"Stamatis Chatzistamatis","orcid":"https://orcid.org/0000-0003-2912-3058"},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stamatis Chatzistamatis","raw_affiliation_strings":["University of the Aegean,I-Lab,Dpt. of Cultural Technology & Communication,Mytilene,Greece,81100"],"affiliations":[{"raw_affiliation_string":"University of the Aegean,I-Lab,Dpt. of Cultural Technology & Communication,Mytilene,Greece,81100","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124281213","display_name":"Nikolaos Evangeliou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120510","display_name":"Information Technology for Market Leadership (Greece)","ror":"https://ror.org/02erc6n26","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210120510"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos Evangeliou","raw_affiliation_strings":["ITML I.K.E.,Information Technology for Market Leadership,Athens,Greece,11525"],"affiliations":[{"raw_affiliation_string":"ITML I.K.E.,Information Technology for Market Leadership,Athens,Greece,11525","institution_ids":["https://openalex.org/I4210120510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120807954","display_name":"Chrysaphis Nathanailidis","orcid":null},"institutions":[{"id":"https://openalex.org/I53074787","display_name":"Technological Educational Institute of Eastern Macedonia and Thrace","ror":"https://ror.org/0009xxz90","country_code":"GR","type":"education","lineage":["https://openalex.org/I53074787"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Chrysaphis Nathanailidis","raw_affiliation_strings":["LIONCODE Lioncode E.E.,Kavala,Greece,64200"],"affiliations":[{"raw_affiliation_string":"LIONCODE Lioncode E.E.,Kavala,Greece,64200","institution_ids":["https://openalex.org/I53074787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084644811","display_name":"George E. Tsekouras","orcid":"https://orcid.org/0000-0001-7006-1536"},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George E. Tsekouras","raw_affiliation_strings":["University of the Aegean,I-Lab,Dpt. of Cultural Technology & Communication,Mytilene,Greece,81100"],"affiliations":[{"raw_affiliation_string":"University of the Aegean,I-Lab,Dpt. of Cultural Technology & Communication,Mytilene,Greece,81100","institution_ids":["https://openalex.org/I98805295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048269612"],"corresponding_institution_ids":["https://openalex.org/I98805295"],"apc_list":null,"apc_paid":null,"fwci":8.3306,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97806116,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.38850000500679016,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.38850000500679016,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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/T10028","display_name":"Topic Modeling","score":0.11800000071525574,"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/T14013","display_name":"Legal Language and Interpretation","score":0.06620000302791595,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5982999801635742},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5498999953269958},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5440999865531921},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48989999294281006},{"id":"https://openalex.org/keywords/legal-document","display_name":"Legal document","score":0.43959999084472656},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4077000021934509},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.37450000643730164}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7401000261306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6942999958992004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6509000062942505},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5982999801635742},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5440999865531921},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C2993995455","wikidata":"https://www.wikidata.org/wiki/Q3150005","display_name":"Legal document","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C521078695","wikidata":"https://www.wikidata.org/wiki/Q4180175","display_name":"Legal practice","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/comcomap68359.2025.11353184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comcomap68359.2025.11353184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Computing, Communications and IoT Applications (ComComAp)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.7363163232803345,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W4317042601","https://openalex.org/W4403508773","https://openalex.org/W4403651347","https://openalex.org/W4406261777","https://openalex.org/W4406892448","https://openalex.org/W4412593420","https://openalex.org/W4415798166","https://openalex.org/W6967149753"],"related_works":[],"abstract_inverted_index":{"Natural":[0],"Language":[1],"Processing":[2],"(NLP)":[3],"pipelines":[4,52,134],"form":[5],"the":[6,128],"backbone":[7],"of":[8,41],"legal":[9,45,66,89,96,114,140],"artificial":[10],"intelligence":[11],"applications,":[12],"yet":[13],"most":[14],"existing":[15],"tools":[16,104],"are":[17],"designed":[18],"for":[19,130],"English":[20,42],"corpora":[21],"and":[22,43,62,91,109,138],"perform":[23],"poorly":[24],"when":[25],"transferred":[26],"to":[27,64,135],"morphologically":[28],"rich,":[29],"non-English":[30],"languages.":[31],"This":[32],"paper":[33],"investigates":[34],"these":[35,77],"limitations":[36],"through":[37],"a":[38,79],"comparative":[39],"study":[40,100],"Greek":[44,113],"texts.":[46],"It":[47],"is":[48,82],"shown":[49],"that":[50,84],"English-centric":[51],"exhibit":[53],"systematic":[54],"errors":[55],"in":[56,68,71,112],"preprocessing":[57],"(tokenization,":[58],"lemmatization,":[59],"stop-word":[60],"removal)":[61],"fail":[63],"capture":[65],"semantics":[67],"embeddings,":[69],"resulting":[70],"degraded":[72],"downstream":[73],"performance.":[74],"To":[75],"address":[76],"issues,":[78],"generalized":[80],"framework":[81],"proposed":[83],"introduces":[85],"language-specific":[86,132],"preprocessing,":[87],"curated":[88],"resources,":[90],"multilingual":[92],"embeddings":[93],"fine-tuned":[94],"on":[95],"corpora.":[97],"A":[98],"case":[99],"demonstrates":[101],"how":[102],"adapted":[103],"substantially":[105],"improve":[106],"similarity":[107],"scores":[108],"classification":[110],"accuracy":[111],"texts,":[115],"while":[116],"highlighting":[117],"persistent":[118],"challenges":[119],"such":[120],"as":[121],"grammatical":[122],"gender":[123],"bias.":[124],"The":[125],"findings":[126],"underscore":[127],"need":[129],"fairness-aware,":[131],"NLP":[133],"support":[136],"robust":[137],"inclusive":[139],"AI":[141],"across":[142],"diverse":[143],"jurisdictions.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2026-01-30T00:00:00"}