BERT pre-entrenado en Twitter sobre las Elecciones de EE.UU. 2020 para la Detección de Posturas hacia Joe Biden (f-BERT)

Este modelo de lenguaje pre-entrenado está ajustado a la tarea de detección de posturas específicamente para Joe Biden. Por favor, consulte el repositorio oficial para más detalles.

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import numpy as np

# elegir GPU si está disponible
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# seleccionar la ruta del modelo aquí
pretrained_LM_path = "kornosk/bert-election2020-twitter-stance-biden"

# cargar el modelo
tokenizer = AutoTokenizer.from_pretrained(pretrained_LM_path)
model = AutoModelForSequenceClassification.from_pretrained(pretrained_LM_path)

id2label = {
  0: "AGAINST",
  1: "FAVOR",
  2: "NONE"
}

##### Predicción Neutral #####
sentence = "Hello World."
inputs = tokenizer(sentence.lower(), return_tensors="pt")
outputs = model(**inputs)
predicted_probability = torch.softmax(outputs[0], dim=1)[0].tolist()

print("Sentence:", sentence)
print("Prediction:", id2label[np.argmax(predicted_probability)])
print("Against:", predicted_probability[0])
print("Favor:", predicted_probability[1])
print("Neutral:", predicted_probability[2])

##### Predicción Favor #####
sentence = "Go Go Biden!!!"
inputs = tokenizer(sentence.lower(), return_tensors="pt")
outputs = model(**inputs)
predicted_probability = torch.softmax(outputs[0], dim=1)[0].tolist()

print("Sentence:", sentence)
print("Prediction:", id2label[np.argmax(predicted_probability)])
print("Against:", predicted_probability[0])
print("Favor:", predicted_probability[1])
print("Neutral:", predicted_probability[2])

##### Predicción Against #####
sentence = "Biden is the worst."
inputs = tokenizer(sentence.lower(), return_tensors="pt")
outputs = model(**inputs)
predicted_probability = torch.softmax(outputs[0], dim=1)[0].tolist()

print("Sentence:", sentence)
print("Prediction:", id2label[np.argmax(predicted_probability)])
print("Against:", predicted_probability[0])
print("Favor:", predicted_probability[1])
print("Neutral:", predicted_probability[2])

Por favor, considere citar nuestro artículo si encuentra esto útil:

Reference

Knowledge Enhance Masked Language Model for Stance Detection, NAACL 2021.

Citation

@inproceedings{kawintiranon2021knowledge,
title={Knowledge Enhanced Masked Language Model for Stance Detection},
author={Kawintiranon, Kornraphop and Singh, Lisa},
booktitle={Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
year={2021},
publisher={Association for Computational Linguistics},
url={https://www.aclweb.org/anthology/2021.naacl-main.376}
}