metadata

language:
  - es
tags:
  - es
  - Sentence Similarity
license: apache-2.0
datasets:
  - stsb_multi_mt(es)
metrics:
  - Cosine-Similarity
  - Manhattan-Distance
  - Euclidean-Distance
  - Dot-Product-Similarity

Training

This model was built using Sentence Transformer.

Model description

Input for the model: Any spanish text Output for the model: encoded text

Evaluation

- Cosine-Similarity :	Pearson: 0.8532 Spearman: 0.8517
- Manhattan-Distance:	Pearson: 0.8289	Spearman: 0.8333
- Euclidean-Distance:	Pearson: 0.8298	Spearman: 0.8340
- Dot-Product-Similarity:	Pearson: 0.8043	Spearman: 0.8063

How to use

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

# You can include sample code which will be formatted
from sentence_transformers import SentenceTransformer
model = SentenceTransformer()
sentences = ["mi nombre es Siddhartha","¿viajas a kathmandu?"]

sentence_embeddings = model.encode(sentences)
print(sentence_embeddings)

Training procedure

I trained on the dataset on the dccuchile/bert-base-spanish-wwm-cased.