
	
		
	
	
		BERT codemixed base model for hinglish (cased)
	



	
		
	
	
		Model description
	


Input for the model: Any codemixed hinglish text
Output for the model: Sentiment. (0 - Negative, 1 - Neutral, 2 - Positive)

I took a bert-base-multilingual-cased model from Huggingface and finetuned it on SAIL 2017 dataset.  

Performance of this model on the SAIL 2017 dataset


	
		
	
	
		Intended uses & limitations
	


Here is how to use this model to get the features of a given text in PyTorch:

and in TensorFlow:

Coming soon!


	
		
	
	
		Training data
	


I trained on the SAIL 2017 dataset link on this pretrained model.


	
		
	
	
		Training procedure
	


No preprocessing.


	
		
	
	
		Eval results
	



	
		
	
	
		BibTeX entry and citation info
	




The bert-base-multilingual-codemixed-cased-sentiment model is a BERT-based model that has been fine-tuned on the SAIL 2017 dataset for sentiment analysis of codemixed Hinglish text. It takes any codemixed Hinglish text as input and predicts the sentiment as negative, neutral, or positive. The model's performance on the SAIL 2017 dataset is not provided. The model requires no preprocessing and can be used in PyTorch or TensorFlow. The training data for this model is the SAIL 2017 dataset, and the training procedure is not specified. No evaluation results are provided, and no BibTeX entry or citation information is available.

Platform did not provide a description for this model.

Rohanrajpal

Models by this creator

bert-base-multilingual-codemixed-cased-sentiment

bert-base-en-es-codemix-cased

bert-base-codemixed-uncased-sentiment

bert-base-en-hi-codemix-cased

Similar creators