---
license: apache-2.0
datasets:
- yelp_polarity
language:
- en
metrics:
- accuracy
library_name: transformers
pipeline_tag: text-classification
---

## Model description
This model is a fine-tuned version of the [bert-base-uncased](https://huggingface.co/transformers/model_doc/bert.html) model to classify the sentiment of yelp reviews. \
The BERT model is finetuned using adversarial training to boost robustness against textual adversarial attacks. 

## How to use

You can use the model with the following code.

```python
from transformers import BertForSequenceClassification, BertTokenizer, TextClassificationPipeline
model_path = "JiaqiLee/robust-bert-yelp"
tokenizer = BertTokenizer.from_pretrained(model_path)
model = BertForSequenceClassification.from_pretrained(model_path, num_labels=2)
pipeline = TextClassificationPipeline(model=model, tokenizer=tokenizer)
print(pipeline("Definitely a greasy spoon! Always packed here and always a wait but worth it."))
```

## Training data
The training data comes from Huggingface [yelp polarity dataset](https://huggingface.co/datasets/yelp_polarity). We use 90% of the `train.csv` data to train the model. \
We augment original training data with adversarial examples generated by PWWS, TextBugger and TextFooler.

## Evaluation results

The model achieves 0.9532 accuracy in yelp polarity test dataset.