Ag Nli DeTS Sentence Similarity V1

🚀 Cross-Encoder for Sentence Similarity

This model is designed to calculate the semantic similarity between two sentences, trained with advanced techniques to provide accurate results.

✨ Features

• Trained using SentenceTransformers Cross-Encoder class.
• Supports multiple languages including English, Dutch, German, French, Italian, and Spanish.
• Predicts a score between 0 (not similar) and 1 (very similar) for sentence pairs.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

Comparing each sentence of sentences1 array to the corresponding sentence of sentences2 array like comparing the first sentence of each array, then comparing the second sentence of each array,...

from sentence_transformers import CrossEncoder

model = CrossEncoder('abbasgolestani/ag-nli-DeTS-sentence-similarity-v1')

# Two lists of sentences
sentences1 = ['I am honored to be given the opportunity to help make our company better',
             'I love my job and what I do here',
             'I am excited about our company’s vision']

sentences2 = ['I am hopeful about the future of our company',
              'My work is aligning with my passion',
              'Definitely our company vision will be the next breakthrough to change the world and I’m so happy and proud to work here']

pairs = zip(sentences1,sentences2)
list_pairs=list(pairs)

scores1 = model.predict(list_pairs, show_progress_bar=False)
print(scores1)

for i in range(len(sentences1)):
    print("{} \t\t {} \t\t Score: {:.4f}".format(sentences1[i], sentences2[i], scores1[i]))

Advanced Usage

Pre-trained models can be used like this:

from sentence_transformers import CrossEncoder
model = CrossEncoder('abbasgolestani/ag-nli-DeTS-sentence-similarity-v1')
scores = model.predict([('Sentence 1', 'Sentence 2'), ('Sentence 3', 'Sentence 4')])

The model will predict scores for the pairs ('Sentence 1', 'Sentence 2') and ('Sentence 3', 'Sentence 4'). You can use this model also without sentence_transformers and by just using Transformers AutoModel class.

📚 Documentation

Training Data

This model was trained on 6 different nli datasets. The model will predict a score between 0 (not similar) and 1 (very similar) for the semantic similarity of two sentences.

Model Information

📄 License

This project is licensed under the Apache-2.0 license.