数据集:

• financial_phrasebank
• chiapudding/kaggle-financial-sentiment
• zeroshot/twitter-financial-news-sentiment
• FinanceInc/auditor_sentiment 语言:
• 英文 库名称: transformers 标签:
• 情感分类
• 金融
• Deberta-v2 许可证: mit

用于金融情感分类的Deberta模型

我使用在亚马逊多评论数据集上训练的Deberta模型（包含超过100万条评论），并在4个带有情感标签分类的金融数据集上进行了微调。所使用的数据集包括：

1. financial_phrasebank
2. chiapudding/kaggle-financial-sentiment
3. zeroshot/twitter-financial-news-sentiment
4. FinanceInc/auditor_sentiment

如何使用该模型

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

def get_sentiment(sentences):
    bert_dict = {}
    vectors = tokenizer(sentences, padding = True, max_length = 65, return_tensors='pt').to(device)
    outputs = bert_model(**vectors).logits
    probs = torch.nn.functional.softmax(outputs, dim = 1)
    for prob in probs:
        bert_dict['neg'] = round(prob[0].item(), 3)
        bert_dict['neu'] = round(prob[1].item(), 3)
        bert_dict['pos'] = round(prob[2].item(), 3)
        print (bert_dict)

MODEL_NAME = 'RashidNLP/Finance-Sentiment-Classification'
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

bert_model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME, num_labels = 3).to(device)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)

get_sentiment(["股市在债务上限提高前将持续承压", "ChatGPT正在提升微软搜索引擎的市场份额"])