The 11th Workshop on
Natural User-generated Text (W-NUT)

Invited Talks

• 

  09:30 – 10:30 Room G15-16 Chair: JinYeong Bak

  Language Identification in the (Pretraining) Data Processing Pipeline – State of the Art and Open Problems

  Hinrich Schütze · Professor, University of Munich

  Abstract to be announced.

  Speaker bio

  Hinrich Schütze is Professor for Computational Linguistics and co-director of the Center for Information and Language Processing at the University of Munich (LMU Munich). He received his PhD from Stanford in 1995 for his early research on embeddings (ACL Test-of-Time Paper Award). He then worked on natural language processing and information retrieval technology at Xerox PARC, at several Silicon Valley startups and at Google 1995-2004 and 2008/9. Hinrich is a coauthor of Foundations of Statistical Natural Language Processing (with Chris Manning) and Introduction to Information Retrieval (with Chris Manning and Prabhakar Raghavan). He was awarded a European Research Council Advanced Grant in 2017. Hinrich served as president of the Association for Computational Linguistics in 2020. He is a member of Academia Europaea and a fellow of ACL, ELLIS, ELIZA and HessianAI.

• 

  14:00 – 15:00 Room G15-16 Chair: Weerayut Buaphet

  Enhancing Multilingual LLMs with Code-Switching

  Haneul Yoo · Assistant Professor/Faculty Fellow, New York University

  Despite recent advances, large language models (LLMs) exhibit uneven performance across languages and often struggle with code-switching—the natural alternation between multiple languages. While code-switching is a common and meaningful mode of human communication, LLMs remain brittle to code-switching inputs, treating them as noise. This talk reframes code-switching as a valuable linguistic signal, exploring how it can be leveraged across the LLM lifecycle, from evaluation, to training, to inference. I will begin with output language alignment (OLA), highlighting systematic failures to respond in the expected language in code-switching contexts. I will also introduce code-switching red-teaming (CSRT), which reveals vulnerabilities in safety and multilingual understanding. I will then present code-switching curriculum learning (CSCL), a data-efficient approach to cross-lingual transfer inspired by human second-language learning. Finally, I will introduce code-switching in-context learning (CSICL), which uses gradual transitions from a target language to English to improve multilingual generalization without additional training.

  Speaker bio

  Haneul Yoo is an Assistant Professor/Faculty Fellow in the Department of Computer Science, Courant Institute School of Mathematics, Computing, and Data Science at New York University. She is also a Research Fellow with the Social Innovation and Special Projects Team in the Division of Policy, Evaluation and Training, Department of Peace Operations at the United Nations. She received her PhD from the School of Computing at KAIST. With a background in machine learning (ML) and natural language processing (NLP), she has worked on (1) developing language models and methods to improve generalization across languages, (2) designing resources and evaluation frameworks for underrepresented languages and cultures, and (3) applying AI in high-stakes, real-world domains for social good. She has published papers in major NLP conferences, including ACL, EMNLP, and NAACL, and has been named a Rising Star at KAIST exploreCSR supported by Google. She has served as a Social Chair at NeurIPS 2026 and co-organized the Multilingual and Equitable Language Technologies (MELT) workshop at COLM 2025, the Women in Machine Learning (WiML) symposium at ICML 2026, and the Generative AI for the World (GenAI4World) workshop at COLM 2026.

• 

  16:00 – 17:00 Room G15-16 Chair: Alan Ramponi

  When Noise Is the Point: What Humanistic Tasks Reveal About Our Data Pipelines

  Maria Antoniak · Assistant Professor, University of Colorado Boulder

  In computational studies of humanistic tasks such as storytelling and poetry, we often encounter datasets whose features frustrate standard NLP pipelines. In this talk, I'll draw on three settings where my collaborators and I have run into this friction. First, I'll discuss user–chatbot conversations like WildChat, where creative requests are long, detailed, and frequently revised, making these logs a rich but also complicated view of how people write with chatbots. Second, I'll describe our development of a fine-grained narrative annotation scheme for very large-scale, heterogeneous web text in pretraining data, where operationalizing a humanities concept is complicated by data diversity. Third, I'll turn to poetry, where the linearization systems used to build training corpora routinely flatten or delete formatting that poets use deliberately. Across these cases, I'll argue that what counts as noise depends on who is reading and for what purpose, and that taking humanistic perspectives seriously can help us build data practices, annotation schemes, and evaluations that better reflect how people actually use language.

  Speaker bio

  Maria Antoniak is an Assistant Professor of Computer Science at the University of Colorado Boulder where she is also affiliated with the Department of Information Science and a member of the Boulder NLP Group. Previously, she was a Young Investigator at the Allen Institute for AI and a postdoc at the Pioneer Centre for AI at the University of Copenhagen. She completed her PhD in Information Science at Cornell University and her master’s degree in Computational Linguistics at the University of Washington. She has also spent time at places like ETH Zürich, Microsoft Research FATE, Twitter Cortex, and Facebook Core Data Science. Her research is in natural language processing and cultural analytics.

Shared Task

Organizers

JinYeong Bak

Associate Professor
SungKyunKwan University

Rob van der Goot

Associate Professor
IT University of Copenhagen

Hyeju Jang

Assistant Professor
Indiana University Indianapolis

Weerayut Buaphet

AI Engineer
Cariva

Alan Ramponi

Senior Researcher
Fondazione Bruno Kessler

Wei Xu

Associate Professor
Georgia Institute of Technology

Alan Ritter

Associate Professor
Georgia Institute of Technology

Contact

JinYeong Bak jy.bak@skku.edu

Program Committee

We thank the W-NUT 2026 program committee members for their contributions to the review process. Members are listed alphabetically by first name.