Papers by Sotaro Takeshita
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. |
ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing statistical phrasal or hierarchical machine translation systems relies on a large set of translation rules which results in engineering challenges. |
| Approach: | They propose to use factorized grammar from the field of linguistics as more general translation rules from XTAG English Grammar to generate a manually crafted summarization dataset. |
| Outcome: | The proposed method outperforms existing methods on low-resource language translation tasks with less training data. |
Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on text embeddings focus less on how information is encoded. |
| Approach: | They find that truncating embedding dimensions causes an increase in performance when removed. |
| Outcome: | The proposed method improves performance across 6 state-of-the-art text encoders and 26 downstream tasks. |
GenGO: ACL Paper Explorer with Semantic Features (2024.acl-demos)
Copied to clipboard
| Challenge: | Scholarly document processing (SDP) is a powerful tool for researchers to process knowledge stored in research papers. |
| Approach: | They propose a system that allows researchers to search papers published in ACL conferences with metadata and text embeddings. |
| Outcome: | The proposed system is simple and efficient to reduce maintenance and financial costs and is extensible to support open development and transparency. |
GenGO Ultra: an LLM-powered ACL Paper Explorer (2025.acl-demo)
Copied to clipboard
| Challenge: | The main repository of natural language processing (NLP) has grown its number of stored papers by 70% from 2019 to 2023. |
| Approach: | They propose an extension to GenGO Ultra which exploits large language models to dynamically generate responses grounded by published papers. |
| Outcome: | The proposed system exploits large language models to generate responses grounded by published papers and performs multi-granularity experiments. |
ROUGE-K: Do Your Summaries Have Keywords? (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing evaluation metrics for extreme summarization models do not pay explicit attention to keywords in summaries, leaving developers ignorant of their presence. |
| Approach: | They propose a keyword-oriented evaluation metric, dubbed ROUGE-K, which quantifies how well summaries include keywords. |
| Outcome: | The proposed model can be extended to include more keywords while keeping the overall quality. |
GerAV: Towards New Heights in German Authorship Verification using Fine-Tuned LLMs on a New Benchmark (2026.findings-acl)
Copied to clipboard
| Challenge: | Authorship verification (AV) is a task of determining whether two texts were written by the same author. |
| Approach: | They propose a benchmark for German AV comprising over 400k labeled text pairs. |
| Outcome: | The proposed model outperforms baselines and state-of-the-art models by 0.09 and surpasses GPT-5 in a zero-shot setting by 0.08. |