5 citations · 9 across the 7 of their papers we have counts for
6 papers · 1 filter
Beyond Atomic Tokens: Factorizing Syllables for Language Model Pretraining
Nghia Hieu Nguyen, Thai Bao Huynh, Binh-An Dinh-Le +4
Conventional tokenizers represent text as characters or statistically derived subwords, overlooking the internal phonological structure of syllables and often requiring large vocab…
MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang +5
This paper presents Murano, an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers…
VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding
Phong Nguyen-Thuan Do, Son Quoc Tran, Phu Gia Hoang +2
The success of Natural Language Understanding (NLU) benchmarks in various languages, such as GLUE for English, CLUE for Chinese, KLUE for Korean, and IndoNLU for Indonesian, has fa…
ViHOS: Hate Speech Spans Detection for Vietnamese
Phu Gia Hoang, Canh Duc Luu, Khanh Quoc Tran +2
The rise in hateful and offensive language directed at other users is one of the adverse side effects of the increased use of social networking platforms. This could make it diffic…
Vietnamese Hate and Offensive Detection using PhoBERT-CNN and Social Media Streaming Data
Khanh Q. Tran, An T. Nguyen, Phu Gia Hoang +3
Society needs to develop a system to detect hate and offense to build a healthy and safe environment. However, current research in this field still faces four major shortcomings, i…
UIT-E10dot3 at SemEval-2021 Task 5: Toxic Spans Detection with Named Entity Recognition and Question-Answering Approaches
Phu Gia Hoang, Luan Thanh Nguyen, Kiet Van Nguyen
The increment of toxic comments on online space is causing tremendous effects on other vulnerable users. For this reason, considerable efforts are made to deal with this, and SemEv…