🚀 ViSoBERT：用于越南社交媒体文本处理的预训练语言模型 (EMNLP 2023 - 主会)

ViSoBERT 是用于越南社交媒体任务的先进语言模型，能够高效处理越南社交媒体文本，为相关自然语言处理任务带来了新的突破。

🚀 快速开始

安装

安装 transformers 和 SentencePiece 包：

pip install transformers
pip install SentencePiece

使用示例

from transformers import AutoModel, AutoTokenizer
import torch

model = AutoModel.from_pretrained('uitnlp/visobert')
tokenizer = AutoTokenizer.from_pretrained('uitnlp/visobert')

encoding = tokenizer('hào quang rực rỡ', return_tensors='pt')

with torch.no_grad():
    output = model(**encoding)

✨ 主要特性

• ViSoBERT 是首个专门为越南社交媒体文本构建的单语 MLM（XLM - R 架构）。
• 在四个下游越南社交媒体任务中，ViSoBERT 超越了以前的单语、多语和多语社交媒体方法，取得了新的先进性能。

📚 详细文档

论文信息

ViSoBERT 的总体架构和实验结果可在我们的 论文 中找到：

@inproceedings{nguyen-etal-2023-visobert,
    title = "{V}i{S}o{BERT}: A Pre-Trained Language Model for {V}ietnamese Social Media Text Processing",
    author = "Nguyen, Nam  and
      Phan, Thang  and
      Nguyen, Duc-Vu  and
      Nguyen, Kiet",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.emnlp-main.315",
    pages = "5191--5207",
    abstract = "English and Chinese, known as resource-rich languages, have witnessed the strong development of transformer-based language models for natural language processing tasks. Although Vietnam has approximately 100M people speaking Vietnamese, several pre-trained models, e.g., PhoBERT, ViBERT, and vELECTRA, performed well on general Vietnamese NLP tasks, including POS tagging and named entity recognition. These pre-trained language models are still limited to Vietnamese social media tasks. In this paper, we present the first monolingual pre-trained language model for Vietnamese social media texts, ViSoBERT, which is pre-trained on a large-scale corpus of high-quality and diverse Vietnamese social media texts using XLM-R architecture. Moreover, we explored our pre-trained model on five important natural language downstream tasks on Vietnamese social media texts: emotion recognition, hate speech detection, sentiment analysis, spam reviews detection, and hate speech spans detection. Our experiments demonstrate that ViSoBERT, with far fewer parameters, surpasses the previous state-of-the-art models on multiple Vietnamese social media tasks. Our ViSoBERT model is available only for research purposes. Disclaimer: This paper contains actual comments on social networks that might be construed as abusive, offensive, or obscene.",
}

预训练数据集

我们论文的预训练数据集可在以下链接获取：预训练数据集

📄 许可证

使用 ViSoBERT 帮助产生已发表的研究成果或集成到其他软件中时，请 引用 我们的论文。

⚠️ 重要提示

⚠️ 重要提示

论文中包含社交网络上的实际评论，可能被视为辱骂、冒犯或淫秽内容。