{"id":"https://openalex.org/W7140096526","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.29","title":"AI Corpus Linguist: More than a Year of Experience","display_name":"AI Corpus Linguist: More than a Year of Experience","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140096526","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.29"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.29","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.29","pdf_url":"https://aclanthology.org/2026.latechclfl-1.29.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.latechclfl-1.29.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029507861","display_name":"Ji\u0159\u00ed Mili\u010dka","orcid":"https://orcid.org/0000-0001-8605-1199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji\u0159\u00ed Mili\u010dka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081565303","display_name":"Tom\u00e1\u0161 Mach\u00e1lek","orcid":"https://orcid.org/0000-0002-0829-4694"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom\u00e1\u0161 Mach\u00e1lek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"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":0.39486011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.21400000154972076,"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":0.21400000154972076,"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/T13629","display_name":"Text Readability and Simplification","score":0.05220000073313713,"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":0.04529999941587448,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.7383000254631042},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5910999774932861},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4729999899864197},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46299999952316284},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4009000062942505},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.382999986410141},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.36649999022483826}],"concepts":[{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.7383000254631042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337999939918518},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6194000244140625},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5910999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5623999834060669},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5320000052452087},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4729999899864197},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.36649999022483826},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.2761000096797943},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C2992676002","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Translation system","level":3,"score":0.2685999870300293}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.latechclfl-1.29","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.29","pdf_url":"https://aclanthology.org/2026.latechclfl-1.29.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-1.29","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.29","pdf_url":"https://aclanthology.org/2026.latechclfl-1.29.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":[{"score":0.6459333896636963,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6303617311","display_name":null,"funder_award_id":"24-11725S","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"}],"funders":[{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140096526.pdf","grobid_xml":"https://content.openalex.org/works/W7140096526.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"AI":[3],"assistant":[4],"designed":[5],"to":[6,27,106],"help":[7],"researchers":[8],"interact":[9],"with":[10,25,66,76],"language":[11,15],"corpora":[12,29],"using":[13],"natural":[14],"instead":[16],"of":[17,57,80],"formal":[18],"query":[19],"languages.Built":[20],"as":[21],"a":[22,55,83],"custom":[23],"GPT":[24],"access":[26],"multilingual":[28],"via":[30],"Czech":[31],"National":[32],"Corpus":[33],"platform":[34],"API,":[35],"the":[36,59,70,96],"system":[37,60,94],"translates":[38],"research":[39,108],"questions":[40],"into":[41],"CQL":[42],"queries,":[43],"retrieves":[44],"corpus":[45,99],"data,":[46],"and":[47,87,112],"guides":[48],"users":[49,111,113],"through":[50],"linguistic":[51,115],"analysis.After":[52],"more":[53],"than":[54],"year":[56],"deployment,":[58],"has":[61],"processed":[62],"over":[63],"1000":[64],"interactions":[65],"human":[67],"users.We":[68],"discuss":[69],"hybrid":[71],"approach":[72],"combining":[73],"rule-based":[74],"translation":[75],"LLM":[77],"intelligence,":[78],"challenges":[79],"building":[81],"on":[82],"constantly":[84],"evolving":[85],"platform,":[86],"lessons":[88],"learned":[89],"from":[90],"production":[91],"usage.Notably,":[92],"this":[93],"represents":[95],"first":[97],"voice-enabled":[98],"interface":[100],"in":[101],"history,":[102],"significantly":[103],"lowering":[104],"barriers":[105],"corpus-based":[107],"for":[109],"non-technical":[110],"outside":[114],"fields.":[116]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}