Home

Awesome

Table of contents

  1. Introduction
  2. Using PhoBERT with transformers
  3. Using PhoBERT with fairseq
  4. Notes

<a name="introduction"></a> PhoBERT: Pre-trained language models for Vietnamese

Pre-trained PhoBERT models are the state-of-the-art language models for Vietnamese (Pho, i.e. "Phở", is a popular food in Vietnam):

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

@inproceedings{phobert,
title     = {{PhoBERT: Pre-trained language models for Vietnamese}},
author    = {Dat Quoc Nguyen and Anh Tuan Nguyen},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020},
year      = {2020},
pages     = {1037--1042}
}

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

<a name="transformers"></a> Using PhoBERT with transformers

Installation <a name="install2"></a>

git clone --single-branch --branch fast_tokenizers_BARTpho_PhoBERT_BERTweet https://github.com/datquocnguyen/transformers.git
cd transformers
pip3 install -e .

Pre-trained models <a name="models2"></a>

Model#paramsArch.Max lengthPre-training dataLicense
vinai/phobert-base-v2135Mbase25620GB of Wikipedia and News texts + 120GB of texts from OSCAR-2301GNU Affero GPL v3
vinai/phobert-base135Mbase25620GB of Wikipedia and News textsMIT License
vinai/phobert-large370Mlarge25620GB of Wikipedia and News textsMIT License

Example usage <a name="usage2"></a>

import torch
from transformers import AutoModel, AutoTokenizer

phobert = AutoModel.from_pretrained("vinai/phobert-base-v2")
tokenizer = AutoTokenizer.from_pretrained("vinai/phobert-base-v2")

# INPUT TEXT MUST BE ALREADY WORD-SEGMENTED!
sentence = 'Chúng_tôi là những nghiên_cứu_viên .'  

input_ids = torch.tensor([tokenizer.encode(sentence)])

with torch.no_grad():
    features = phobert(input_ids)  # Models outputs are now tuples

## With TensorFlow 2.0+:
# from transformers import TFAutoModel
# phobert = TFAutoModel.from_pretrained("vinai/phobert-base")

<a name="fairseq"></a> Using PhoBERT with fairseq

Please see details at HERE!

<a name="vncorenlp"></a> Notes

In case the input texts are raw, i.e. without word segmentation, a word segmenter must be applied to produce word-segmented texts before feeding to PhoBERT. As PhoBERT employed the RDRSegmenter from VnCoreNLP to pre-process the pre-training data (including Vietnamese tone normalization and word and sentence segmentation), it is recommended to also use the same word segmenter for PhoBERT-based downstream applications w.r.t. the input raw texts.

Installation

pip install py_vncorenlp

Example usage <a name="example"></a>

import py_vncorenlp

# Automatically download VnCoreNLP components from the original repository
# and save them in some local machine folder
py_vncorenlp.download_model(save_dir='/absolute/path/to/vncorenlp')

# Load the word and sentence segmentation component
rdrsegmenter = py_vncorenlp.VnCoreNLP(annotators=["wseg"], save_dir='/absolute/path/to/vncorenlp')

text = "Ông Nguyễn Khắc Chúc  đang làm việc tại Đại học Quốc gia Hà Nội. Bà Lan, vợ ông Chúc, cũng làm việc tại đây."

output = rdrsegmenter.word_segment(text)

print(output)
# ['Ông Nguyễn_Khắc_Chúc đang làm_việc tại Đại_học Quốc_gia Hà_Nội .', 'Bà Lan , vợ ông Chúc , cũng làm_việc tại đây .']