Revision 13 as of 2025-08-12 23:21:18

Clear message

Locked History Actions

KarolinaSaputa

Karolina Saputa

Final farewell

This is a very sad time. Karolina Saputa, our colleague at the Linguistic Engineering Group has passed away. She was a young, talented person, full of ideas and passion. This is a huge loss.

ka.png

She participated in numerous natural language processing projects, including CLARIN-PL: Common Language Resources and Technological Infrastructure and Universal Discourse: a multilingual model of discourse relations.

She spoke at many conferences, including recently Data & AI Warsaw Tech Summit, Centre of Excellence in Social Sciences Masterclass in Text Analysis Workshop, Google Developer Group CloudFest Poland or CLARIN-PL Workshop.

She authored many publications (see below) and inspired interdisciplinary research on coreference, discourse processing, corpus creation and Large Language Models.

We will miss her.

Her publications

List of publications

2024

Karol Saputa, Angelika Peljak-Łapińska, and Maciej Ogrodniczuk. Polish Coreference Corpus as an LLM testbed: Evaluating coreference resolution within instruction-following language models by instruction–answer alignment. In Maciej Ogrodniczuk, Anna Nedoluzhko, Massimo Poesio, Sameer Pradhan, and Vincent Ng, editors, Proceedings of The Seventh Workshop on Computational Models of Reference, Anaphora and Coreference, pages 23–32, Miami, 2024. Association for Computational Linguistics.

2023

Karol Saputa, Aleksandra Tomaszewska, Natalia Zawadzka-Paluektau, Witold Kieraś, and Łukasz Kobyliński. Korpusomat.eu: A multilingual platform for building and analysing linguistic corpora. In Jiří Mikyška, Clélia de Mulatier, Maciej Paszynski, Valeria V. Krzhizhanovskaya, Jack J. Dongarra, and Peter M.A. Sloot, editors, Computational Science – ICCS 2023. 23rd International Conference, Prague, Czech Republic, July 3–5, 2023, Proceedings, Part II, number 14074 in Lecture Notes in Computer Science, pages 230–237, Cham, 2023. Springer Nature Switzerland.

Anna Wróblewska, Bartosz Pieliński, Karolina Seweryn, Sylwia Sysko-Romańczuk, Karol Saputa, Aleksandra Wichrowska, and Hanna Schreiber. Automating the analysis of institutional design in international agreements. In Jiří Mikyška, Clélia de Mulatier, Maciej Paszynski, Valeria V. Krzhizhanovskaya, Jack J. Dongarra, and Peter M.A. Sloot, editors, Computational Science – ICCS 2023, pages 59–73, Cham, 2023. Springer Nature Switzerland.

2022

Karol Saputa. Coreference resolution for Polish: Improvements within the CRAC 2022 shared task. In Zdeněk Žabokrtský and Maciej Ogrodniczuk, editors, Proceedings of the CRAC 2022 Shared Task on Multilingual Coreference Resolution, pages 18–22, Gyeongju, Republic of Korea, 2022. Association for Computational Linguistics.

Anna Wróblewska, Bartosz Pieliński, Karolina Seweryn, Karol Saputa, Aleksandra Wichrowska, Sylwia Sysko-Romańczuk, and Hanna Schreiber. Entity graph extraction from legal acts – a prototype for a use case in policy design analysis, 2022. arXiv:2209.00944.

2020

Karol Saputa, Małgorzata Wachulec, and Aleksandra Wichrowska. Building an explainable model for ordinal classification on Eucalyptus dataset. Meeting black box model performance levels, 2020.