edumunozsala's picture
Fix Metric Typos (#1)
6a506e8
metadata
language: es
tags:
  - sagemaker
  - roberta-bne
  - TextClassification
  - SentimentAnalysis
license: apache-2.0
datasets:
  - IMDbreviews_es
metrics:
  - accuracy
model-index:
  - name: roberta_bne_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: 0.9106666666666666
          - name: F1 Score
            type: f1
            value: 0.9090909090909091
          - name: Precision
            type: precision
            value: 0.9063852813852814
          - name: Recall
            type: recall
            value: 0.9118127381600436
widget:
  - text: >-
      Se trata de una película interesante, con un solido argumento y un gran
      interpretación de su actor principal

Model roberta_bne_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 RoBERTa-base-bne which is a RoBERTa base model and has been pre-trained using the largest Spanish corpus known to date, with a total of 570GB. It was trained by The National Library of Spain (Biblioteca Nacional de España)

RoBERTa BNE Citation Check out the paper for all the details: https://arxiv.org/abs/2107.07253

@article{gutierrezfandino2022,
    author = {Asier Gutiérrez-Fandiño and Jordi Armengol-Estapé and Marc Pàmies and Joan Llop-Palao and Joaquin Silveira-Ocampo and Casimiro Pio Carrino and Carme Armentano-Oller and Carlos Rodriguez-Penagos and Aitor Gonzalez-Agirre and Marta Villegas},
    title = {MarIA: Spanish Language Models},
    journal = {Procesamiento del Lenguaje Natural},
    volume = {68},
    number = {0},
    year = {2022},
    issn = {1989-7553},
    url = {http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6405},
    pages = {39--60}
}

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": "\"PlanTL-GOB-ES/roberta-base-bne\"",
"sagemaker_container_log_level": "20",
"sagemaker_program": "\"train.py\"",
}

Evaluation results

  • Accuracy = 0.9106666666666666

  • F1 Score = 0.9090909090909091

  • Precision = 0.9063852813852814

  • Recall = 0.9118127381600436

Test results

Model in action

Usage for Sentiment Analysis

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("edumunozsala/roberta_bne_sentiment_analysis_es")
model = AutoModelForSequenceClassification.from_pretrained("edumunozsala/roberta_bne_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