Otto
Tarkka
Project Researcher, Data analytics
Doctoral Researcher, Digital Language Studies, Chinese, French, German, Italian, Spanish
MA
turkunlp.org
Contact
Areas of expertise
natural language processing
linguistics
digital linguistics
corpus-assisted discourse analysis
Biography
I started studying English at the University of Turku in 2016 and got my Bachelor's degree three years later. My BA thesis was a corpus linguistic study on learner English. After my BA, I almost accidentally enrolled on a course called 'Automatic Text Processing' and was immediately hooked. I decided to do my MA in Digital Language Studies and wrote my MA thesis on topic modelling. During my studies I worked with the fine people at the TurkuNLP research group and have been working on my PhD with them since 2023.
Research
I am a PhD student currently doing research as part of the GreenNLP project at TurkuNLP. I am interested in machine learning, Large Language Models and applying these emerging technologies in corpus linguistic research.
Publications
Automated Emotion Annotation of Finnish Parliamentary Speeches Using GPT-4 (2024)
ParlaCLARIN Workshop, LREC Proceedings
(A4 Vertaisarvioitu artikkeli konferenssijulkaisussa)
Towards diverse and contextually anchored paraphrase modeling: A dataset and baselines for Finnish (2023)
Natural Language Engineering
(Vertaisarvioitu alkuperäisartikkeli tai data-artikkeli tieteellisessä aikakauslehdessä (A1))
Mistä koronapandemian aikana keskustellaan sosiaalisessa mediassa? (2022)
(Yleistajuinen artikkeli tai blogikirjoitus (E1))Textual Paraphrase Dataset for Deep Language Modelling (2022)
(Vertaisarvioitu artikkeli kokoomateoksessa (A3))Finnish Paraphrase Corpus (2021)
Nordic Conference on Computational Linguistics, Linköping Electronic Conference Proceedings
(Vertaisarvioitu artikkeli konferenssijulkaisussa (A4))