--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers license: cc-by-4.0 language: ta widget: - source_sentence: "மக்கள் குழு பாடுகிறது" sentences: - "சிலர் பாடுகிறார்கள்" - "ஒரு இளைஞன் பியானோ பாடுகிறான்" - "மனிதன் ஒரு கடிதம் எழுதுகிறான்" example_title: "Example 1" - source_sentence: "நாய் பொம்மையை குரைக்கிறது" sentences: - "ஒரு நாய் ஒரு பொம்மையில் குரைக்கிறது" - "ஒரு பூனை பால் குடிக்கிறது" - "ஒரு நாய் ஒரு பந்தைத் துரத்துகிறது" example_title: "Example 2" - source_sentence: "நான் முதல் முறையாக விமானத்தில் அமர்ந்தேன்" sentences: - "அது எனது முதல் விமானப் பயணம் " - "முதல் முறையாக ரயிலில் அமர்ந்தேன்" - "புதிய இடங்களுக்கு பயணம் செய்வது எனக்கு மிகவும் பிடிக்கும்" example_title: "Example 3" --- # TamilSBERT This is a TamilBERT model (l3cube-pune/tamil-bert) trained on the NLI dataset.
Released as a part of project MahaNLP: https://github.com/l3cube-pune/MarathiNLP
A multilingual version of this model supporting major Indic languages and cross-lingual capabilities is shared here indic-sentence-bert-nli
A better sentence similarity model (fine-tuned version of this model) is shared here: https://huggingface.co/l3cube-pune/tamil-sentence-similarity-sbert
More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2304.11434) ``` @article{deode2023l3cube, title={L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT}, author={Deode, Samruddhi and Gadre, Janhavi and Kajale, Aditi and Joshi, Ananya and Joshi, Raviraj}, journal={arXiv preprint arXiv:2304.11434}, year={2023} } ``` ``` @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} } ``` monolingual Indic SBERT paper
multilingual Indic SBERT paper Other Monolingual Indic sentence BERT models are listed below:
Marathi SBERT
Hindi SBERT
Kannada SBERT
Telugu SBERT
Malayalam SBERT
Tamil SBERT
Gujarati SBERT
Oriya SBERT
Bengali SBERT
Punjabi SBERT
Indic SBERT (multilingual)
Other Monolingual similarity models are listed below:
Marathi Similarity
Hindi Similarity
Kannada Similarity
Telugu Similarity
Malayalam Similarity
Tamil Similarity
Gujarati Similarity
Oriya Similarity
Bengali Similarity
Punjabi Similarity
Indic Similarity (multilingual)
## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python 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) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), 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. ```python 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) ```