Papers by Ilker Kesen
Multilingual Pretraining for Pixel Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | PIXEL-M4 model pretrains on four visually and linguistically diverse languages . previous work on pixel-based language models focused on monolingual pretraining on English data . |
| Approach: | They propose a pixel-based language model that is pretrained on four visually diverse languages. |
| Outcome: | The proposed model outperforms an English-only counterpart on non-Latin scripts on semantic and syntactic tasks. |
CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data (2026.acl-long)
Copied to clipboard
Pedro Ortiz Suarez, Laurie Burchell, Catherine Arnett, Rafael Mosquera, Sara Hincapié Monsalve, Thom Vaughan, Damian Stewart, Malte Ostendorff, Idris Abdulmumin, Vukosi Marivate, Shamsuddeen Hassan Muhammad, Atnafu Lambebo Tonja, Hend Al-Khalifa, Nadia Ghezaiel Hammouda, Verrah Akinyi Otiende, Tack Hwa Wong, Jakhongir Saydaliev, Melika Nobakhtian, Muhammad Ravi Shulthan Habibi, Chalamalasetti Kranti, Carol Muchemi, Khang Nguyen, Faisal Muhammad Adam, Luis Frentzen Salim, Reem Alqifari, Cynthia Jayne Amol, Joseph Marvin Imperial, Ilker Kesen, Ahmad Mustafid, Pavel Stepachev, Leshem Choshen, David Anugraha, Hamada Nayel, Seid Muhie Yimam, Vallerie Alexandra Putra, My Chiffon Nguyen, Azmine Toushik Wasi, Gouthami Vadithya, Rob Van Der Goot, Lanwenn ar C’horr, Karan Dua, Andrew Yates, Mithil Bangera, Yeshil Bangera, Hitesh Laxmichand Patel, Shu Okabe, Fenal Ashokbhai Ilasariya, Dmitry Gaynullin, Genta Indra Winata, Yiyuan Li, Juan Pablo Martínez, Amit Agarwal, Ikhlasul Akmal Hanif, Raia Abu Ahmad, Esther Adenuga, Filbert Aurelian Tjiaranata, Weerayut Buaphet, Michael Anugraha, Sowmya Vajjala, Benjamin L Rice, Azril Hafizi Amirudin, Jesujoba Oluwadara Alabi, Srikant Panda, Yassine Toughrai, Bruhan Kyomuhendo, Daniel Ruffinelli, null Akshata, Manuel Goulão, Ej Zhou, Ingrid Gabriela Franco Ramirez, Cristina Aggazzotti, Konstantin Dobler, Jun Kevin, Quentin Pagès, Nicholas Andrews, Nuhu Ibrahim, Mattes Ruckdeschel, Amr Keleg, Mike Zhang, Casper Rufaro Muziri, Saron Samuel, Sotaro Takeshita, Kun Kerdthaisong, Luca Foppiano, Rasul Dent, Tommaso Green, Ahmad Mustapha Wali, Kamohelo Makaaka, Vicky Feliren, Inshirah Idris, Hande Celikkanat, Abdulhamid Abubakar, Jean Maillard, Benoît Sagot, Thibault Clérice, Kenton Murray, Sarah K. K. Luger
| Challenge: | Language identification (LID) is a fundamental step in curating multilingual corpora. |
| Approach: | They introduce CommonLID, a community-driven, human-annotated LID benchmark for the web domain, covering 109 languages. |
| Outcome: | The proposed benchmark covers 109 languages and shows that existing evaluations overestimate accuracy for many languages in the web domain. |
CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions (2022.findings-acl)
Copied to clipboard
Tayfun Ates, M. Ateşoğlu, Çağatay Yiğit, Ilker Kesen, Mert Kobas, Erkut Erdem, Aykut Erdem, Tilbe Goksun, Deniz Yuret
| Challenge: | Existing models with similar physical and causal understanding capabilities are still underdeveloped. |
| Approach: | They propose a video question answering dataset that requires causal reasoning about physical forces and object interactions. |
| Outcome: | The proposed dataset requires causal reasoning about physical forces and object interactions. |
Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing Turkish benchmarks lack task diversity or culturally relevant content . Cetvel combines a broad range of discriminative and generative tasks . |
| Approach: | They propose a benchmark to evaluate large language models in Turkish . Cetvel combines a broad range of discriminative and generative tasks . they find that Turkish-centric instruction-tuned models generally underperform . |
| Outcome: | The proposed benchmark covers 23 tasks grouped into seven categories . it shows that Turkish-centric instruction-tuned models underperform relative to multilingual or general-purpose models despite being tailored for the language. |