Bertin Roberta Base Finetuning Esnli

🚀 bertin-roberta-base-finetuning-esnli

This is a sentence-transformers model trained on a collection of NLI tasks for Spanish. It maps sentences and paragraphs to a 768-dimensional dense vector space and can be used for tasks such as clustering or semantic search. Based on the siamese networks approach from this paper.

📋 Model Information

You can see a demo for this model here.

You can find our other model, paraphrase-spanish-distilroberta here and its demo here.

🚀 Quick Start

📦 Installation

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

pip install -U sentence-transformers

💻 Usage Examples

🔍 Basic Usage

from sentence_transformers import SentenceTransformer
sentences = ["Este es un ejemplo", "Cada oración es transformada"]

model = SentenceTransformer('hackathon-pln-es/bertin-roberta-base-finetuning-esnli')
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('hackathon-pln-es/bertin-roberta-base-finetuning-esnli')
model = AutoModel.from_pretrained('hackathon-pln-es/bertin-roberta-base-finetuning-esnli')

# 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)

📊 Evaluation Results

Our model was evaluated on the task of Semantic Textual Similarity using the SemEval-2015 Task for Spanish.

🔧 Technical Details

🏋️‍ Training

The model was trained with the following parameters:

• Dataset: We used a collection of datasets of Natural Language Inference as training data, including ESXNLI (Spanish part only), SNLI (automatically translated), and MultiNLI (automatically translated). The whole dataset used is available here.
• DataLoader: sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader of length 1818 with parameters {'batch_size': 64}.
• Loss: sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss with parameters {'scale': 20.0, 'similarity_fct': 'cos_sim'}.
• Fit()-Method Parameters:

{
    "epochs": 10,
    "evaluation_steps": 0,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 909,
    "weight_decay": 0.01
}

📐 Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 514, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

👥 Authors

• Anibal Pérez
• Emilio Tomás Ariza
• Lautaro Gesuelli
• Mauricio Mazuecos