Hindi Sentence Similarity Sbert

🚀 HindSBERT-STS

This is a model designed for sentence similarity tasks. It is a fine - tuned version of the HindSBERT model ( l3cube - pune/hindi - sentence - bert - nli ) on the STS dataset. It was released as part of the project MahaNLP: https://github.com/l3cube - pune/MarathiNLP. A multilingual version of this model, which supports major Indic languages and cross - lingual sentence similarity, is available at indic - sentence - similarity - sbert .

🚀 Quick Start

Prerequisites

This is a sentence - transformers model. It maps sentences and paragraphs to a 768 - dimensional dense vector space and can be used for tasks such as clustering or semantic search.

Installation

Using this model becomes easy when you have sentence - transformers installed:

pip install -U sentence-transformers

Basic Usage

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage

Without sentence - transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling - operation on top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

📚 Documentation

Model Details

More details on the dataset, models, and baseline results can be found in our paper

@article{joshi2022l3cubemahasbert,
  title={L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi},
  author={Joshi, Ananya and Kajale, Aditi and Gadre, Janhavi and Deode, Samruddhi and Joshi, Raviraj},
  journal={arXiv preprint arXiv:2211.11187},
  year={2022}
}

Related Papers

• monolingual Indic SBERT paper
• multilingual Indic SBERT paper

Related Models

Monolingual Similarity Models

• Marathi Similarity
• Hindi Similarity
• Kannada Similarity
• Telugu Similarity
• Malayalam Similarity
• Tamil Similarity
• Gujarati Similarity
• Oriya Similarity
• Bengali Similarity
• Punjabi Similarity
• Indic Similarity (multilingual)

Monolingual Indic Sentence BERT Models

• Marathi SBERT
• Hindi SBERT
• Kannada SBERT
• Telugu SBERT
• Malayalam SBERT
• Tamil SBERT
• Gujarati SBERT
• Oriya SBERT
• Bengali SBERT
• Punjabi SBERT
• Indic SBERT (multilingual)

📄 License

This model is released under the cc - by - 4.0 license.

🔍 Widget Examples

Example 1

• Source Sentence: "एक आदमी एक रस्सी पर चढ़ रहा है"
• Comparison Sentences:
  • "एक आदमी एक रस्सी पर चढ़ता है"
  • "एक आदमी एक दीवार पर चढ़ रहा है"
  • "एक आदमी बांसुरी बजाता है"

Example 2

• Source Sentence: "कुछ लोग गा रहे हैं"
• Comparison Sentences:
  • "लोगों का एक समूह गाता है"
  • "बिल्ली दूध पी रही है"
  • "दो आदमी लड़ रहे हैं"

Example 3

• Source Sentence: "फेडरर ने 7वां विंबलडन खिताब जीत लिया है"
• Comparison Sentences:
  • "फेडरर अपने करियर में कुल 20 ग्रैंडस्लैम खिताब जीत चुके है "
  • "फेडरर ने सितंबर में अपने निवृत्ति की घोषणा की"
  • "एक आदमी कुछ खाना पकाने का तेल एक बर्तन में डालता है"