{"id":"https://openalex.org/W7140145003","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.3","title":"Studying Expert-ese: Profiling and Classification of Domain-Specific Language Variation in Architecture with Traditional Machine Learning and LLMs","display_name":"Studying Expert-ese: Profiling and Classification of Domain-Specific Language Variation in Architecture with Traditional Machine Learning and LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140145003","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.3"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.3","pdf_url":"https://aclanthology.org/2026.latechclfl-1.3.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 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.latechclfl-1.3.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130406797","display_name":"Carmen Schacht","orcid":null},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carmen Schacht","raw_affiliation_strings":["Ruhr-University Bochum , Germany Faculty of Philology Department of Linguistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ruhr-University Bochum , Germany Faculty of Philology Department of Linguistics","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026407048","display_name":"Renate Delucchi Danhier","orcid":"https://orcid.org/0000-0002-8247-815X"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Renate Delucchi Danhier","raw_affiliation_strings":["TU Dortmund University Department of Cultural Studies Institute for Diversity Studies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dortmund University Department of Cultural Studies Institute for Diversity Studies","institution_ids":["https://openalex.org/I200332995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.25554223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.13989999890327454,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.13989999890327454,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.12380000203847885,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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":0.06729999929666519,"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/profiling","display_name":"Profiling (computer programming)","score":0.7337999939918518},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5737000107765198},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5447999835014343},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.2962999939918518},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.25609999895095825}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7337999939918518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6342999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6330000162124634},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4593000113964081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45579999685287476},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.23229999840259552}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.latechclfl-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.3","pdf_url":"https://aclanthology.org/2026.latechclfl-1.3.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 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.3","pdf_url":"https://aclanthology.org/2026.latechclfl-1.3.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 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6460915207862854}],"awards":[{"id":"https://openalex.org/G1951765764","display_name":null,"funder_award_id":"SFB 1102","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G737504480","display_name":"SFB 1102: Informationsdichte und sprachliche Kodierung","funder_award_id":"232722074","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/W7140145003.pdf","grobid_xml":"https://content.openalex.org/works/W7140145003.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"investigates":[2],"how":[3],"domain":[4,127],"expertise":[5,150],"shapes":[6],"spontaneous":[7,156],"oral":[8],"language":[9,84],"production,":[10],"with":[11,26,77],"a":[12,43,78],"focus":[13],"on":[14,16,140],"architecture.Building":[15],"the":[17,39,90,103,109,143,159],"ExpLay":[18],"Corpus,":[19],"which":[20],"contains":[21],"image":[22],"descriptions":[23],"by":[24,35],"speakers":[25],"and":[27,38,48,58,73,81,87,92,117,133],"without":[28],"architectural":[29,149],"training,":[30],"we":[31],"analyze":[32],"linguistic":[33,53,153],"variation":[34,128],"combining":[36],"Profiling-UD":[37],"DECAF":[40],"framework.We":[41],"extract":[42],"broad":[44],"range":[45],"of":[46,126,161],"syntactic":[47],"morpho-syntactic":[49],"features":[50,132],"to":[51,61],"build":[52],"profiles":[54],"for":[55],"both":[56,114],"groups":[57],"train":[59],"classifiers":[60],"distinguish":[62],"expert":[63,91],"from":[64],"non-expert":[65,93],"productions.Two":[66],"traditional":[67,115],"machine":[68],"learning":[69],"models":[70,85,116],"(logistic":[71],"regression":[72],"SVM)":[74],"are":[75,123],"compared":[76],"lightweight":[79],"BiLSTM":[80,104],"two":[82],"large":[83],"(GliClass":[86],"LLaMA":[88],"2).While":[89],"corpora":[94],"diverge":[95],"only":[96],"subtly":[97],"(pairwise":[98],"Jensen-Shannon":[99],"divergence":[100],"(JSD)=":[101],"0.25),":[102],"using":[105],"fastText":[106],"embeddings":[107],"achieves":[108],"highest":[110],"F1score":[111],"(0.88),":[112],"outperforming":[113],"LLMs.This":[118],"indicates":[119],"that":[120,134,148],"semantic":[121],"representations":[122],"more":[124],"predictive":[125],"than":[129],"purely":[130],"structural":[131],"smaller":[135],"neural":[136],"architectures":[137],"generalize":[138],"better":[139],"limited":[141],"data.Overall,":[142],"findings":[144],"provide":[145],"empirical":[146],"evidence":[147],"leaves":[151],"measurable":[152],"traces":[154],"in":[155],"speech,":[157],"supporting":[158],"Grammar":[160],"Space":[162],"hypothesis.":[163]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-03-24T00:00:00"}