distilbert-base-fallacy-classification

项目介绍：distilbert-base-fallacy-classification

项目背景

distilbert-base-fallacy-classification 是一个针对逻辑谬误检测任务进行了微调的模型版本。它基于 distilbert-base-uncased 模型，并使用 Logical Fallacy Dataset 数据集进行训练。此模型的主要任务是对不同类别的逻辑谬误进行文本分类。

模型描述

该模型能够识别和分类14种不同的逻辑谬误类别，具体包括：人身攻击、诉诸多数、诉诸情感、循环论证、模棱两可、信誉谬误、扩展谬误、逻辑谬误、相关性谬误、虚假因果、错误二分、错误概括、意图谬误，以及其他类别。

使用示例

一个简单的示例展示了如何使用该模型对文本进行逻辑谬误分类。以下是代码示例：

from transformers import pipeline

text = "We know that the earth is flat because it looks and feels flat."
model_path = "q3fer/distilbert-base-fallacy-classification"
pipe = pipeline("text-classification", model=model_path, tokenizer=model_path)
pipe(text)

运行以上代码后，模型将预测给定文本的逻辑谬误类别，例如识别出“循环论证”的可能性为0.9511。

完整分类示例

以下代码展示了获取推理的完整结果：

import torch
from transformers import AutoTokenizer
from transformers import AutoModelForSequenceClassification

model = AutoModelForSequenceClassification.from_pretrained("q3fer/distilbert-base-fallacy-classification")
tokenizer = AutoTokenizer.from_pretrained("q3fer/distilbert-base-fallacy-classification")

text = "We know that the earth is flat because it looks and feels flat."
inputs = tokenizer(text, return_tensors='pt')

with torch.no_grad():
  logits = model(**inputs)
  scores = logits[0][0]
  scores = torch.nn.Softmax(dim=0)(scores)

  _, ranking = torch.topk(scores, k=scores.shape[0])
  ranking = ranking.tolist()

results = [f"{i+1}) {model.config.id2label[ranking[i]]} {scores[ranking[i]]:.4f}" for i in range(scores.shape[0])]
print('\n'.join(results))