@inproceedings{nguyen-tuan-nguyen-2020-phobert,
    title = "{P}ho{BERT}: Pre-trained language models for {V}ietnamese",
    author = "Nguyen, Dat Quoc  and
      Tuan Nguyen, Anh",
    editor = "Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.findings-emnlp.92/",
    doi = "10.18653/v1/2020.findings-emnlp.92",
    pages = "1037--1042",
    abstract = "We present PhoBERT with two versions, PhoBERT-base and PhoBERT-large, the first public large-scale monolingual language models pre-trained for Vietnamese. Experimental results show that PhoBERT consistently outperforms the recent best pre-trained multilingual model XLM-R (Conneau et al., 2020) and improves the state-of-the-art in multiple Vietnamese-specific NLP tasks including Part-of-speech tagging, Dependency parsing, Named-entity recognition and Natural language inference. We release PhoBERT to facilitate future research and downstream applications for Vietnamese NLP. Our PhoBERT models are available at \url{https://github.com/VinAIResearch/PhoBERT}"
}