📰 Check out our newest EACL 2023 Work
Read moreExplore VietAI Research Works
An Artificial Intelligence Hub where you can read about our new state-of-the-art Deep Learning works.
Natural Language Processing
Enriching Biomedical Knowledge for Low-resource Language Through Translation
We present ViT5, a pretrained Transformer-based encoder-decoder model for the Vietnamese language that achieves state-of-the-art results on Vietnamese Text Summarization
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation
We present ViT5, a pretrained Transformer-based encoder-decoder model for the Vietnamese language that achieves state-of-the-art results on Vietnamese Text Summarization
MTet: Multi-domain Translation for English and Vietnamese
We introduce our second release of VietAI’s MTet project, which stands for Multi-domain Translation for English and VieTnamese. With this release, we further improved on the first-ever multi-domain English-Vietnamese translation dataset at scale to release up to 4.2M examples across 11 domains. In addition, we demonstrated state-of-the-art results on IWSLT’15 (+3.5 BLEU for English-Vietnamese).
Topics
Our Researchers and Students are working on a wide-range of topics in AI
Translation
Summarization
Text Generation
More articles
Enriching Biomedical Knowledge for Low-resource Language Through Translation
We present ViT5, a pretrained Transformer-based encoder-decoder model for the Vietnamese language that achieves state-of-the-art results on Vietnamese Text Summarization
MTet: Multi-domain Translation for English and Vietnamese
We introduce our second release of VietAI’s MTet project, which stands for Multi-domain Translation for English and VieTnamese. With this release, we further improved on the first-ever multi-domain English-Vietnamese translation dataset at scale to release up to 4.2M examples across 11 domains. In addition, we demonstrated state-of-the-art results on IWSLT’15 (+3.5 BLEU for English-Vietnamese).
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation
We present ViT5, a pretrained Transformer-based encoder-decoder model for the Vietnamese language that achieves state-of-the-art results on Vietnamese Text Summarization