Gk Hinglish Sentiment

🚀 Sentiment Classification for hinglish text: gk-hinglish-sentiment

This project focuses on sentiment classification for Hinglish text, aiming to provide an effective solution for analyzing sentiment in the Hinglish language.

🚀 Quick Start

Basic Usage

#sample code 
from transformers import BertTokenizer, BertForSequenceClassification
tokenizerg = BertTokenizer.from_pretrained("/content/model")
modelg = BertForSequenceClassification.from_pretrained("/content/model")

text = "kuch bhi type karo hinglish mai"
encoded_input = tokenizerg(text, return_tensors='pt')
output = modelg(**encoded_input)
print(output)
#output contains 3 lables LABEL_0 = Negative ,LABEL_1 = Nuetral ,LABEL_2 = Positive

✨ Features

• This model is designed to work well with Hinglish data, which is widely used in India.
• It can classify sentiment into three labels: negative, neutral, and positive.

📦 Installation

The README does not provide specific installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

#sample code 
from transformers import BertTokenizer, BertForSequenceClassification
tokenizerg = BertTokenizer.from_pretrained("/content/model")
modelg = BertForSequenceClassification.from_pretrained("/content/model")

text = "kuch bhi type karo hinglish mai"
encoded_input = tokenizerg(text, return_tensors='pt')
output = modelg(**encoded_input)
print(output)
#output contains 3 lables LABEL_0 = Negative ,LABEL_1 = Nuetral ,LABEL_2 = Positive

📚 Documentation

Model description

The model was trained on a small amount of reviews dataset.

Intended uses & limitations

The author wanted a model that could work well with Hinglish data, which is mostly used in India. However, the training data was limited.

Limitations and bias

The data only contains Hinglish codemixed text and is very limited. The author may update the model if more data is available.

Training data

The training data contains labeled data for 3 labels. The model was tuned based on the pre - trained model at https://huggingface.co/rohanrajpal/bert-base-multilingual-codemixed-cased-sentiment.

BibTeX entry and citation info

    title = "{GLUEC}o{S}: An Evaluation Benchmark for Code-Switched {NLP}",
    author = "Khanuja, Simran  and
      Dandapat, Sandipan  and
      Srinivasan, Anirudh  and
      Sitaram, Sunayana  and
      Choudhury, Monojit",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-main.329",
    pages = "3575--3585"
}

📄 License

The model is licensed under the Apache 2.0 license.