SubmissionNumber#=%=#44
FinalPaperTitle#=%=#AI Corpus Linguist: More than a Year of Experience
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Jiri Milicka
JobTitle#==#
Organization#==#Charles University
Ovocný trh 560/5, 116 36 Prague 1, Czech Republic
Abstract#==#We present an AI assistant designed to help researchers interact with language corpora using natural language instead of formal query languages. Built as a custom GPT with access to multilingual corpora via Czech National Corpus platform API, the system translates research questions into CQL queries, retrieves corpus data, and guides users through linguistic analysis. After more than a year of deployment, the system has processed over 1000 interactions with human users. We discuss the hybrid approach combining rule-based translation with LLM intelligence, challenges of building on a constantly evolving platform, and lessons learned from production usage. Notably, this system represents the first voice-enabled corpus interface in history, significantly lowering barriers to corpus-based research for non-technical users and users outside linguistic fields.
Author{1}{Firstname}#=%=#Jiří
Author{1}{Lastname}#=%=#Milička
Author{1}{Username}#=%=#jirimilicka
Author{1}{Orcid}#=%=#https://orcid.org/0000-0001-8605-1199
Author{1}{Email}#=%=#milicka@centrum.cz
Author{1}{Affiliation}#=%=#Institute of Comparative Linguistics, Faculty of Arts, Charles University, Prague
Author{2}{Firstname}#=%=#Tomáš
Author{2}{Lastname}#=%=#Machálek
Author{2}{Username}#=%=#machalekt
Author{2}{Orcid}#=%=#
Author{2}{Email}#=%=#tomas.machalek@ff.cuni.cz
Author{2}{Affiliation}#=%=#Charles University, Faculty of Arts

==========
èéáğö