Oak Ridge National Laboratory, US
Tirthankar Ghosal is a scientist (Artificial Intelligence and High Performance Computing) at the Oak Ridge National Laboratory, US. His research interests are Foundational NLP Models, Cognitive NLP, NLP for Scholarly Communications and Peer Review, Argumentation Mining, and Text/Dialogue Summarization. He was the principal organizer of the first iteration of the AutoMin shared task at Interspeech 2021 and also the SummDial special sessions at SIGDial 2021 and SemDial 2022 on meeting and dialogue summarization. He is currently the co-editor of the SIGIR Forum. Tirthankar has served/serving in organization committees of several international conferences and workshops including ArgKG @ AKBC 2021, SDP @ EMNLP 2020, SDP @ NAACL 2021, ICON 2020, EurNLP 2021, WiNLP 2020, mini-WiNLP @ AACL-IJCNLP 2020/EACL/ACL/NAACL 2021, WiNLP @ EMNLP 2021, FORCE 2021, and a shared task on Argumentation Mining (SciVer) at 2nd SDP @ NAACL 2021. Tirthankar is passionate on working in issues related diversity and inclusion in the research community. He was the Diversity and Inclusion (D&I) co-chair at AACL-IJCNLP, ACL 2020 (Financial Access), NAACL 2019 (Financial Access) and a past chair of the Widening NLP initiative.
Charles University, Prague, Czech Republic
Ondrej Bojar is an associate professor at the Institute of Formal and Applied Linguistics, Charles University, Prague. His main research interest is machine translation but he was also involved in treebanking and lexicographic projects at the department. He participated the Johns Hopkins University Summer Engineering Workshop in 2006 as a member of the Moses team. Since then, he has been regularly taking part in WMT shared translation tasks and co-organizing them since 2013, with specific focus on translation into Czech, on MT evaluation (WMT Metrics Task) and training aspects of both “classical” statistical MT (SMT) and neural MT. He has been the main local organizer of MT Marathons held in Prague (2009, 2013, 2015, 2016, 2018). He teaches courses on SMT and NMT and machine learning, supervises many batchelor theses, some master theses and several PhD students. He has been working on several national research projects and two EU-funded projects: EuroMatrix (2006–2009), EuroMatrixPlus (2009–2012), MosesCore (2012–2015), QT21, HimL, CRACKER (all 2015–2018), being the local lead technical developer and manager in them since 2011.
Naver Labs Europe, France
Laurent Besacier is a principal scientist at Naver Labs Europe since January 2021. Before that, he was a professor at the University Grenoble Alpes (UGA) where he led the natural language and speech processing group of LIG lab. His main research expertise and interests lie in the field of natural language processing, automatic speech recognition and the evaluation of NLP systems. He is a co-author of the ELITR-Bench paper which inspired task B of this challenge.
Naver Labs Europe, France
Thibaut Thonet is a research scientist at Naver Labs Europe in Grenoble, France since 2019. Thibaut's current research focuses on natural language processing, machine learning and information retrieval, with a special interest in the alignment and control of large language models. Previously, Thibaut worked on recommender systems and co-organized the GReS workshop at RecSys 2021. Thibaut also co-authored the ELITR-Bench paper which served as the foundation for task B in AutoMin 2025.