BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese

Two BARTpho versions BARTpho-syllable and BARTpho-word are the first public large-scale monolingual sequence-to-sequence models pre-trained for Vietnamese. BARTpho uses the "large" architecture and pre-training scheme of the sequence-to-sequence denoising model BART, thus especially suitable for generative NLP tasks. Experiments on a downstream task of Vietnamese text summarization show that in both automatic and human evaluations, BARTpho outperforms the strong baseline mBART and improves the state-of-the-art.

The general architecture and experimental results of BARTpho can be found in our paper:

@article{bartpho,
title     = {{BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese}},
author    = {Nguyen Luong Tran and Duong Minh Le and Dat Quoc Nguyen},
journal   = {arXiv preprint},
volume    = {arXiv:2109.09701},
year      = {2021}
}

Please CITE our paper when BARTpho is used to help produce published results or incorporated into other software.

For further information or requests, please go to BARTpho's homepage!

Downloads last month
5,060
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for vinai/bartpho-word

Finetunes
6 models