2026-10-01
From 21 to 24 September 2026, the Department of Simultaneous Translation of the Faculty of Humanities at Kyrgyz-Turkish Manas University hosted the international workshop "Natural Language Processing (NLP) Technologies and Corpus Linguistics." The workshop was led by Dr. Marie-Pauline Krielke and Dr. Andrea Wurm of Saarland University, Germany, together with Prof. Dr. Aida Kasieva of KTMU.
The workshop opened on 21 September with the opening lecture of Prof. Dr. Aida Kasieva where she reported on corpus linguistics for Kyrgyz: the work done so far, the open questions and plans for the future. In the onboarding session that followed, participants presented their research interests and were introduced to the tools used in the course.
On 22–23 September, Dr. Krielke's sessions covered how to turn raw texts into annotated corpora, how to work with metadata and linguistic annotation, how to query corpora with regular expressions, and how to use AI in corpus analysis. One block was devoted to Universal Dependencies in practice, including AI-assisted parsing, evaluation and annotation quality. Dr. Wurm showed how to download, visualize and analyze query results for discourse analysis using Sketch Engine and free tools.
On 24 September, Dr. Wurm covered two topics. The first was the move from corpus linguistics to qualitative data analysis with MAXQDA, TEI/XML and open-source tools. The second was how to compile, annotate and analyze parallel corpora of learner translations, including how to adapt manual annotation schemes.
Every lecture was followed by a hands-on session in which participants applied the methods to real data. The workshop ended with a closing session, an evaluation and the award of certificates.
The training built up the department's capacity for corpus-based and computational research on Kyrgyz, English and other languages. It also strengthened the partnership between KTMU and Saarland University and opened the way to joint projects, publications and new language resources.


