|
--- |
|
language: es |
|
tags: |
|
- sagemaker |
|
- bertin |
|
- TextClassification |
|
- SentimentAnalysis |
|
license: apache-2.0 |
|
datasets: |
|
- IMDbreviews_es |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bertin_base_sentiment_analysis_es |
|
results: |
|
- task: |
|
name: Sentiment Analysis |
|
type: sentiment-analysis |
|
dataset: |
|
name: "IMDb Reviews in Spanish" |
|
type: IMDbreviews_es |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.898933 |
|
- name: F1 Score |
|
type: f1 |
|
value: 0.8989063 |
|
- name: Precision |
|
type: precision |
|
value: 0.8771473 |
|
- name: Recall |
|
type: recall |
|
value: 0.9217724 |
|
widget: |
|
- text: "Se trata de una película interesante, con un solido argumento y un gran interpretación de su actor principal" |
|
--- |
|
|
|
# Model bertin_base_sentiment_analysis_es |
|
|
|
## **A finetuned model for Sentiment analysis in Spanish** |
|
|
|
This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container, |
|
The base model is **Bertin base** which is a RoBERTa-base model pre-trained on the Spanish portion of mC4 using Flax. |
|
It was trained by the Bertin Project.[Link to base model](https://huggingface.co/bertin-project/bertin-roberta-base-spanish) |
|
|
|
Article: BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Sampling |
|
- Author = Javier De la Rosa y Eduardo G. Ponferrada y Manu Romero y Paulo Villegas y Pablo González de Prado Salas y María Grandury, |
|
- journal = Procesamiento del Lenguaje Natural, |
|
- volume = 68, number = 0, year = 2022 |
|
- url = http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6403 |
|
|
|
## Dataset |
|
The dataset is a collection of movie reviews in Spanish, about 50,000 reviews. The dataset is balanced and provides every review in english, in spanish and the label in both languages. |
|
|
|
Sizes of datasets: |
|
- Train dataset: 42,500 |
|
- Validation dataset: 3,750 |
|
- Test dataset: 3,750 |
|
|
|
## Intended uses & limitations |
|
|
|
This model is intented for Sentiment Analysis for spanish corpus and finetuned specially for movie reviews but it can be applied to other kind of reviews. |
|
|
|
## Hyperparameters |
|
{ |
|
"epochs": "4", |
|
"train_batch_size": "32", |
|
"eval_batch_size": "8", |
|
"fp16": "true", |
|
"learning_rate": "3e-05", |
|
"model_name": "\"bertin-project/bertin-roberta-base-spanish\"", |
|
"sagemaker_container_log_level": "20", |
|
"sagemaker_program": "\"train.py\"", |
|
} |
|
|
|
## Evaluation results |
|
|
|
- Accuracy = 0.8989333333333334 |
|
|
|
- F1 Score = 0.8989063750333421 |
|
|
|
- Precision = 0.877147319104633 |
|
|
|
- Recall = 0.9217724288840262 |
|
|
|
## Test results |
|
|
|
## Model in action |
|
|
|
### Usage for Sentiment Analysis |
|
|
|
```python |
|
import torch |
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("edumunozsala/bertin_base_sentiment_analysis_es") |
|
model = AutoModelForSequenceClassification.from_pretrained("edumunozsala/bertin_base_sentiment_analysis_es") |
|
|
|
text ="Se trata de una película interesante, con un solido argumento y un gran interpretación de su actor principal" |
|
|
|
input_ids = torch.tensor(tokenizer.encode(text)).unsqueeze(0) |
|
outputs = model(input_ids) |
|
output = outputs.logits.argmax(1) |
|
``` |
|
|
|
Created by [Eduardo Muñoz/@edumunozsala](https://github.com/edumunozsala) |
|
|
