BERT PT Laptop

🚀 ReviewBERT

ReviewBERT is a BERT model (post-)trained on review corpora to understand sentiment, options, and various aspects of e-commerce.

🚀 Quick Start

Model Variants

• BERT-DK_laptop is trained on a 100MB laptop corpus under Electronics/Computers & Accessories/Laptops.
• BERT-PT_* additionally uses SQuAD 1.1.

✨ Features

Model Description

The original model is BERT-base-uncased, which was trained on Wikipedia + BookCorpus. The models are post-trained on the Amazon Dataset and Yelp Dataset.

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoModel, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("activebus/BERT-PT_laptop")
model = AutoModel.from_pretrained("activebus/BERT-PT_laptop")

📚 Documentation

Evaluation Results

Check our NAACL paper

📄 License

Citation

If you find this work useful, please cite as follows:

@inproceedings{xu_bert2019,
    title = "BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis",
    author = "Xu, Hu and Liu, Bing and Shu, Lei and Yu, Philip S.",
    booktitle = "Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics",
    month = "jun",
    year = "2019",
}