Papers by Luan Thanh Nguyen
ViHateT5: Enhancing Hate Speech Detection in Vietnamese With a Unified Text-to-Text Transformer Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for HSD in Vietnamese focus on fine-tuning general pre-trained models, primarily trained on formal textual datasets like Wikipedia. |
| Approach: | They propose a T5-based HSD model pre-trained on a domain-specific dataset . their results highlight the significance of label distribution in pre-training data on model efficacy. |
| Outcome: | The proposed model can tackle multiple tasks using a unified model and achieve state-of-the-art performance across all standard HSD benchmarks in Vietnamese. |
Multi-Dialect Vietnamese: Task, Dataset, Baseline Models and Challenges (2024.emnlp-main)
Copied to clipboard
| Challenge: | Vietnamese is a low-resource language, but each province has its own distinct pronunciation variations. |
| Approach: | They propose a dataset that captures the rich diversity of 63 provincial dialects spoken in Vietnam. |
| Outcome: | The proposed dataset captures the rich diversity of 63 provincial dialects spoken across Vietnam. |