Papers by Xuan-Son Vu
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code (2025.coling-industry)
Copied to clipboard
Taishi Nakamura, Mayank Mishra, Simone Tedeschi, Yekun Chai, Jason T. Stillerman, Felix Friedrich, Prateek Yadav, Tanmay Laud, Vu Minh Chien, Terry Yue Zhuo, Diganta Misra, Ben Bogin, Xuan-Son Vu, Marzena Karpinska, Arnav Varma Dantuluri, Wojciech Kusa, Tommaso Furlanello, Rio Yokota, Niklas Muennighoff, Suhas Pai, Tosin Adewumi, Veronika Laippala, Xiaozhe Yao, Adalberto Barbosa Junior, Aleksandr Drozd, Jordan Clive, Kshitij Gupta, Liangyu Chen, Qi Sun, Ken Tsui, Nour Moustafa-Fahmy, Nicolo Monti, Tai Dang, Ziyang Luo, Tien-Tung Bui, Roberto Navigli, Virendra Mehta, Matthew Blumberg, Victor May, Hiep Nguyen, Sampo Pyysalo
| Challenge: | Pretrained language models are integral part of AI applications, but their high computational cost limits accessibility. |
| Approach: | They evaluate Aurora-M, a 15B parameter multilingual open-source model trained on English, Finnish, Hindi, Japanese, Vietnamese, and code. |
| Outcome: | The proposed model outperforms existing models on English, Finnish, Hindi, Japanese, Vietnamese, and code. |
ViGPTQA - State-of-the-Art LLMs for Vietnamese Question Answering: System Overview, Core Models Training, and Evaluations (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) and their applications in low-resource languages are limited due to lack of training data and benchmarking datasets. |
| Approach: | They propose a question-response system for Vietnamese that uses LLMs . they propose to open-source the model and train it on benchmark datasets based on Vietnamese data . |
| Outcome: | The proposed question answering system for Vietnamese is open-source and performant . it can learn and capture human-like text, but there is a gap in evaluations for Vietnamese . |
Multimodal Review Generation with Privacy and Fairness Awareness (2020.coling-main)
Copied to clipboard
| Challenge: | Existing frameworks for generating personalized reviews take privacy and fairness into account . users generate digital footprints when "traveling" on the internet . |
| Approach: | They propose a neural-based framework that generates personalized reviews with privacy and fairness in mind. |
| Outcome: | The proposed framework generates plausibly long reviews while controlling the amount of exploited user data and using the least sentiment biased embeddings. |
Pseudonymization Categories across Domain Boundaries (2024.lrec-main)
Copied to clipboard
Maria Irena Szawerna, Simon Dobnik, Therese Lindström Tiedemann, Ricardo Muñoz Sánchez, Xuan-Son Vu, Elena Volodina
| Challenge: | Linguistic data can contain personal information, which is limited in accessibility . a universal system of tags for categorizing PIIs could be developed to replace them . |
| Approach: | They analyze tagsets used for anonymization and pseudonymization to find out what kinds of PII appear in different domains. |
| Outcome: | The proposed system would allow for dynamic pseudonymization while keeping the data readable and useful for future research. |