Papers by Long Phan
Enriching Biomedical Knowledge for Low-resource Language Through Large-scale Translation (2023.eacl-main)
Copied to clipboard
| Challenge: | Biomedical data and benchmarks are highly valuable but limited in low-resource languages such as English. |
| Approach: | They propose a translation model in Vietnamese that trains a pretrained Encoder-Decoder Transformer model on 20 million translated abstracts. |
| Outcome: | The proposed model can translate and produce both pretrained and supervised biomedical data in two biomedically important domains. |
Palmyra 3.0: A User-Friendly Cloud-Based Platform for Morphology and Dependency Syntax Annotation (2024.lrec-main)
Copied to clipboard
| Challenge: | Palmyra 3.0 is a cloud-based platform for morphology and syntax annotation. |
| Approach: | They present Palmyra 3.0, a cloud-based platform for morphology and syntax annotation. |
| Outcome: | Palmyra 3.0 provides configuration files for a number of predefined formalisms, such as UD and CATiB, and a variety of user-friendly features to support annotators. |
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation (2022.naacl-srw)
Copied to clipboard
| Challenge: | Existing models for the English language have been used to train on large corpus of high-quality texts. |
| Approach: | They present a pretrained Transformer-based encoder-decoder model for the Vietnamese language . they benchmark ViT5 on two downstream text generation tasks . |
| Outcome: | The proposed model outperforms existing models on Vietnamese Abstractive Summarization and Named Entity Recognition tasks. |