A new multilingual sentiment analysis module has been added.
This commit is contained in:
@@ -182,6 +182,7 @@ WeiboSentiment_Finetuned/GPT2-AdapterTuning/models/
|
|||||||
WeiboSentiment_Finetuned/BertChinese-Lora/models/
|
WeiboSentiment_Finetuned/BertChinese-Lora/models/
|
||||||
WeiboSentiment_LLM/models/
|
WeiboSentiment_LLM/models/
|
||||||
WeiboSentiment_Finetuned/BertChinese-Lora/model/
|
WeiboSentiment_Finetuned/BertChinese-Lora/model/
|
||||||
|
WeiboMultilingualSentiment/model/
|
||||||
|
|
||||||
# LoRA 和 Adapter 权重
|
# LoRA 和 Adapter 权重
|
||||||
*/adapter_model.safetensors
|
*/adapter_model.safetensors
|
||||||
|
|||||||
@@ -0,0 +1,119 @@
|
|||||||
|
# 多语言情感分析 - Multilingual Sentiment Analysis
|
||||||
|
|
||||||
|
本模块使用HuggingFace上的多语言情感分析模型进行情感分析,支持22种语言。
|
||||||
|
|
||||||
|
## 模型信息
|
||||||
|
|
||||||
|
- **模型名称**: tabularisai/multilingual-sentiment-analysis
|
||||||
|
- **基础模型**: distilbert-base-multilingual-cased
|
||||||
|
- **支持语言**: 22种语言,包括:
|
||||||
|
- 中文 (中文)
|
||||||
|
- English (英语)
|
||||||
|
- Español (西班牙语)
|
||||||
|
- 日本語 (日语)
|
||||||
|
- 한국어 (韩语)
|
||||||
|
- Français (法语)
|
||||||
|
- Deutsch (德语)
|
||||||
|
- Русский (俄语)
|
||||||
|
- العربية (阿拉伯语)
|
||||||
|
- हिन्दी (印地语)
|
||||||
|
- Português (葡萄牙语)
|
||||||
|
- Italiano (意大利语)
|
||||||
|
- 等等...
|
||||||
|
|
||||||
|
- **输出类别**: 5级情感分类
|
||||||
|
- 非常负面 (Very Negative)
|
||||||
|
- 负面 (Negative)
|
||||||
|
- 中性 (Neutral)
|
||||||
|
- 正面 (Positive)
|
||||||
|
- 非常正面 (Very Positive)
|
||||||
|
|
||||||
|
## 快速开始
|
||||||
|
|
||||||
|
1. 确保已安装依赖:
|
||||||
|
```bash
|
||||||
|
pip install transformers torch
|
||||||
|
```
|
||||||
|
|
||||||
|
2. 运行预测程序:
|
||||||
|
```bash
|
||||||
|
python predict.py
|
||||||
|
```
|
||||||
|
|
||||||
|
3. 输入任意语言的文本进行分析:
|
||||||
|
```
|
||||||
|
请输入文本: I love this product!
|
||||||
|
预测结果: 非常正面 (置信度: 0.9456)
|
||||||
|
```
|
||||||
|
|
||||||
|
4. 查看多语言示例:
|
||||||
|
```
|
||||||
|
请输入文本: demo
|
||||||
|
```
|
||||||
|
|
||||||
|
## 代码示例
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
||||||
|
import torch
|
||||||
|
|
||||||
|
# 加载模型
|
||||||
|
model_name = "tabularisai/multilingual-sentiment-analysis"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||||
|
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
||||||
|
|
||||||
|
# 预测
|
||||||
|
texts = [
|
||||||
|
"今天心情很好", # 中文
|
||||||
|
"I love this!", # 英文
|
||||||
|
"¡Me encanta!" # 西班牙文
|
||||||
|
]
|
||||||
|
|
||||||
|
for text in texts:
|
||||||
|
inputs = tokenizer(text, return_tensors="pt")
|
||||||
|
outputs = model(**inputs)
|
||||||
|
prediction = torch.argmax(outputs.logits, dim=1).item()
|
||||||
|
sentiment_map = {0: "非常负面", 1: "负面", 2: "中性", 3: "正面", 4: "非常正面"}
|
||||||
|
print(f"{text} -> {sentiment_map[prediction]}")
|
||||||
|
```
|
||||||
|
|
||||||
|
## 特色功能
|
||||||
|
|
||||||
|
- **多语言支持**: 无需指定语言,自动识别22种语言
|
||||||
|
- **5级精细分类**: 比传统二分类更细致的情感分析
|
||||||
|
- **高精度**: 基于DistilBERT的先进架构
|
||||||
|
- **本地缓存**: 首次下载后保存到本地,加快后续使用
|
||||||
|
|
||||||
|
## 应用场景
|
||||||
|
|
||||||
|
- 国际社交媒体监控
|
||||||
|
- 多语言客户反馈分析
|
||||||
|
- 全球产品评论情感分类
|
||||||
|
- 跨语言品牌情感追踪
|
||||||
|
- 多语言客服优化
|
||||||
|
- 国际市场研究
|
||||||
|
|
||||||
|
## 模型存储
|
||||||
|
|
||||||
|
- 首次运行时会自动下载模型到当前目录的 `model` 文件夹
|
||||||
|
- 后续运行会直接从本地加载,无需重复下载
|
||||||
|
- 模型大小约135MB,首次下载需要网络连接
|
||||||
|
|
||||||
|
## 文件说明
|
||||||
|
|
||||||
|
- `predict.py`: 主预测程序,使用直接模型调用
|
||||||
|
- `README.md`: 使用说明
|
||||||
|
|
||||||
|
## 注意事项
|
||||||
|
|
||||||
|
- 首次运行时会自动下载模型,需要网络连接
|
||||||
|
- 模型会保存到当前目录,方便后续使用
|
||||||
|
- 支持GPU加速,会自动检测可用设备
|
||||||
|
- 如需清理模型文件,删除 `model` 文件夹即可
|
||||||
|
- 该模型基于合成数据训练,在实际应用中建议进行验证
|
||||||
|
|
||||||
|
## 参考信息
|
||||||
|
|
||||||
|
- 模型链接: https://huggingface.co/tabularisai/multilingual-sentiment-analysis
|
||||||
|
- 许可证: CC-BY-NC-4.0 (非商业使用)
|
||||||
|
- 商业使用需联系: info@tabularis.ai
|
||||||
@@ -0,0 +1,173 @@
|
|||||||
|
import torch
|
||||||
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
|
||||||
|
import re
|
||||||
|
|
||||||
|
def preprocess_text(text):
|
||||||
|
"""简单的文本预处理,适用于多语言文本"""
|
||||||
|
text = re.sub(r"\{%.+?%\}", " ", text) # 去除 {%xxx%}
|
||||||
|
text = re.sub(r"@.+?( |$)", " ", text) # 去除 @xxx
|
||||||
|
text = re.sub(r"【.+?】", " ", text) # 去除 【xx】
|
||||||
|
text = re.sub(r"\u200b", " ", text) # 去除特殊字符
|
||||||
|
text = re.sub(r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+", "", text) # 去除URL
|
||||||
|
# 删除表情符号
|
||||||
|
text = re.sub(r'[\U0001F600-\U0001F64F\U0001F300-\U0001F5FF\U0001F680-\U0001F6FF\U0001F1E0-\U0001F1FF\U00002600-\U000027BF\U0001f900-\U0001f9ff\U0001f018-\U0001f270\U0000231a-\U0000231b\U0000238d-\U0000238d\U000024c2-\U0001f251]+', '', text)
|
||||||
|
text = re.sub(r"\s+", " ", text) # 多个空格合并
|
||||||
|
return text.strip()
|
||||||
|
|
||||||
|
def main():
|
||||||
|
print("正在加载多语言情感分析模型...")
|
||||||
|
|
||||||
|
# 使用多语言情感分析模型
|
||||||
|
model_name = "tabularisai/multilingual-sentiment-analysis"
|
||||||
|
local_model_path = "./model"
|
||||||
|
|
||||||
|
try:
|
||||||
|
# 检查本地是否已有模型
|
||||||
|
import os
|
||||||
|
if os.path.exists(local_model_path):
|
||||||
|
print("从本地加载模型...")
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(local_model_path)
|
||||||
|
model = AutoModelForSequenceClassification.from_pretrained(local_model_path)
|
||||||
|
else:
|
||||||
|
print("首次使用,正在下载模型到本地...")
|
||||||
|
# 下载并保存到本地
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||||
|
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
||||||
|
|
||||||
|
# 保存到本地
|
||||||
|
tokenizer.save_pretrained(local_model_path)
|
||||||
|
model.save_pretrained(local_model_path)
|
||||||
|
print(f"模型已保存到: {local_model_path}")
|
||||||
|
|
||||||
|
# 设置设备
|
||||||
|
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
||||||
|
model.to(device)
|
||||||
|
model.eval()
|
||||||
|
print(f"模型加载成功! 使用设备: {device}")
|
||||||
|
|
||||||
|
# 情感标签映射(5级分类)
|
||||||
|
sentiment_map = {
|
||||||
|
0: "非常负面", 1: "负面", 2: "中性", 3: "正面", 4: "非常正面"
|
||||||
|
}
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
print(f"模型加载失败: {e}")
|
||||||
|
print("请检查网络连接")
|
||||||
|
return
|
||||||
|
|
||||||
|
print("\n============= 多语言情感分析 =============")
|
||||||
|
print("支持语言: 中文、英文、西班牙文、阿拉伯文、日文、韩文等22种语言")
|
||||||
|
print("情感等级: 非常负面、负面、中性、正面、非常正面")
|
||||||
|
print("输入文本进行分析 (输入 'q' 退出):")
|
||||||
|
print("输入 'demo' 查看多语言示例")
|
||||||
|
|
||||||
|
while True:
|
||||||
|
text = input("\n请输入文本: ")
|
||||||
|
if text.lower() == 'q':
|
||||||
|
break
|
||||||
|
|
||||||
|
if text.lower() == 'demo':
|
||||||
|
show_multilingual_demo(tokenizer, model, device, sentiment_map)
|
||||||
|
continue
|
||||||
|
|
||||||
|
if not text.strip():
|
||||||
|
print("输入不能为空,请重新输入")
|
||||||
|
continue
|
||||||
|
|
||||||
|
try:
|
||||||
|
# 预处理文本
|
||||||
|
processed_text = preprocess_text(text)
|
||||||
|
|
||||||
|
# 分词编码
|
||||||
|
inputs = tokenizer(
|
||||||
|
processed_text,
|
||||||
|
max_length=512,
|
||||||
|
padding=True,
|
||||||
|
truncation=True,
|
||||||
|
return_tensors='pt'
|
||||||
|
)
|
||||||
|
|
||||||
|
# 转移到设备
|
||||||
|
inputs = {k: v.to(device) for k, v in inputs.items()}
|
||||||
|
|
||||||
|
# 预测
|
||||||
|
with torch.no_grad():
|
||||||
|
outputs = model(**inputs)
|
||||||
|
logits = outputs.logits
|
||||||
|
probabilities = torch.softmax(logits, dim=1)
|
||||||
|
prediction = torch.argmax(probabilities, dim=1).item()
|
||||||
|
|
||||||
|
# 输出结果
|
||||||
|
confidence = probabilities[0][prediction].item()
|
||||||
|
label = sentiment_map[prediction]
|
||||||
|
|
||||||
|
print(f"预测结果: {label} (置信度: {confidence:.4f})")
|
||||||
|
|
||||||
|
# 显示所有类别的概率
|
||||||
|
print("详细概率分布:")
|
||||||
|
for i, (label_name, prob) in enumerate(zip(sentiment_map.values(), probabilities[0])):
|
||||||
|
print(f" {label_name}: {prob:.4f}")
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
print(f"预测时发生错误: {e}")
|
||||||
|
continue
|
||||||
|
|
||||||
|
def show_multilingual_demo(tokenizer, model, device, sentiment_map):
|
||||||
|
"""展示多语言情感分析示例"""
|
||||||
|
print("\n=== 多语言情感分析示例 ===")
|
||||||
|
|
||||||
|
demo_texts = [
|
||||||
|
# 中文
|
||||||
|
("今天天气真好,心情特别棒!", "中文"),
|
||||||
|
("这家餐厅的菜味道非常棒!", "中文"),
|
||||||
|
("服务态度太差了,很失望", "中文"),
|
||||||
|
|
||||||
|
# 英文
|
||||||
|
("I absolutely love this product!", "英文"),
|
||||||
|
("The customer service was disappointing.", "英文"),
|
||||||
|
("The weather is fine, nothing special.", "英文"),
|
||||||
|
|
||||||
|
# 日文
|
||||||
|
("このレストランの料理は本当に美味しいです!", "日文"),
|
||||||
|
("このホテルのサービスはがっかりしました。", "日文"),
|
||||||
|
|
||||||
|
# 韩文
|
||||||
|
("이 가게의 케이크는 정말 맛있어요!", "韩文"),
|
||||||
|
("서비스가 너무 별로였어요。", "韩文"),
|
||||||
|
|
||||||
|
# 西班牙文
|
||||||
|
("¡Me encanta cómo quedó la decoración!", "西班牙文"),
|
||||||
|
("El servicio fue terrible y muy lento.", "西班牙文"),
|
||||||
|
]
|
||||||
|
|
||||||
|
for text, language in demo_texts:
|
||||||
|
try:
|
||||||
|
inputs = tokenizer(
|
||||||
|
text,
|
||||||
|
max_length=512,
|
||||||
|
padding=True,
|
||||||
|
truncation=True,
|
||||||
|
return_tensors='pt'
|
||||||
|
)
|
||||||
|
|
||||||
|
inputs = {k: v.to(device) for k, v in inputs.items()}
|
||||||
|
|
||||||
|
with torch.no_grad():
|
||||||
|
outputs = model(**inputs)
|
||||||
|
logits = outputs.logits
|
||||||
|
probabilities = torch.softmax(logits, dim=1)
|
||||||
|
prediction = torch.argmax(probabilities, dim=1).item()
|
||||||
|
|
||||||
|
confidence = probabilities[0][prediction].item()
|
||||||
|
label = sentiment_map[prediction]
|
||||||
|
|
||||||
|
print(f"\n{language}: {text}")
|
||||||
|
print(f"结果: {label} (置信度: {confidence:.4f})")
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
print(f"处理 {text} 时出错: {e}")
|
||||||
|
|
||||||
|
print("\n=== 示例结束 ===")
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
@@ -8,6 +8,8 @@ def preprocess_text(text):
|
|||||||
text = re.sub(r"@.+?( |$)", " ", text) # 去除 @xxx
|
text = re.sub(r"@.+?( |$)", " ", text) # 去除 @xxx
|
||||||
text = re.sub(r"【.+?】", " ", text) # 去除 【xx】
|
text = re.sub(r"【.+?】", " ", text) # 去除 【xx】
|
||||||
text = re.sub(r"\u200b", " ", text) # 去除特殊字符
|
text = re.sub(r"\u200b", " ", text) # 去除特殊字符
|
||||||
|
# 删除表情符号
|
||||||
|
text = re.sub(r'[\U0001F600-\U0001F64F\U0001F300-\U0001F5FF\U0001F680-\U0001F6FF\U0001F1E0-\U0001F1FF\U00002600-\U000027BF\U0001f900-\U0001f9ff\U0001f018-\U0001f270\U0000231a-\U0000231b\U0000238d-\U0000238d\U000024c2-\U0001f251]+', '', text)
|
||||||
text = re.sub(r"\s+", " ", text) # 多个空格合并
|
text = re.sub(r"\s+", " ", text) # 多个空格合并
|
||||||
return text.strip()
|
return text.strip()
|
||||||
|
|
||||||
|
|||||||
@@ -7,6 +7,8 @@ def preprocess_text(text):
|
|||||||
text = re.sub(r"@.+?( |$)", " ", text) # 去除 @xxx
|
text = re.sub(r"@.+?( |$)", " ", text) # 去除 @xxx
|
||||||
text = re.sub(r"【.+?】", " ", text) # 去除 【xx】
|
text = re.sub(r"【.+?】", " ", text) # 去除 【xx】
|
||||||
text = re.sub(r"\u200b", " ", text) # 去除特殊字符
|
text = re.sub(r"\u200b", " ", text) # 去除特殊字符
|
||||||
|
# 删除表情符号
|
||||||
|
text = re.sub(r'[\U0001F600-\U0001F64F\U0001F300-\U0001F5FF\U0001F680-\U0001F6FF\U0001F1E0-\U0001F1FF\U00002600-\U000027BF\U0001f900-\U0001f9ff\U0001f018-\U0001f270\U0000231a-\U0000231b\U0000238d-\U0000238d\U000024c2-\U0001f251]+', '', text)
|
||||||
text = re.sub(r"\s+", " ", text) # 多个空格合并
|
text = re.sub(r"\s+", " ", text) # 多个空格合并
|
||||||
return text.strip()
|
return text.strip()
|
||||||
|
|
||||||
|
|||||||
@@ -1,6 +1,18 @@
|
|||||||
import torch
|
import torch
|
||||||
from transformers import BertTokenizer
|
from transformers import BertTokenizer
|
||||||
from train import GPT2ClassifierWithAdapter
|
from train import GPT2ClassifierWithAdapter
|
||||||
|
import re
|
||||||
|
|
||||||
|
def preprocess_text(text):
|
||||||
|
"""简单的文本预处理"""
|
||||||
|
text = re.sub(r"\{%.+?%\}", " ", text) # 去除 {%xxx%}
|
||||||
|
text = re.sub(r"@.+?( |$)", " ", text) # 去除 @xxx
|
||||||
|
text = re.sub(r"【.+?】", " ", text) # 去除 【xx】
|
||||||
|
text = re.sub(r"\u200b", " ", text) # 去除特殊字符
|
||||||
|
# 删除表情符号
|
||||||
|
text = re.sub(r'[\U0001F600-\U0001F64F\U0001F300-\U0001F5FF\U0001F680-\U0001F6FF\U0001F1E0-\U0001F1FF\U00002600-\U000027BF\U0001f900-\U0001f9ff\U0001f018-\U0001f270\U0000231a-\U0000231b\U0000238d-\U0000238d\U000024c2-\U0001f251]+', '', text)
|
||||||
|
text = re.sub(r"\s+", " ", text) # 多个空格合并
|
||||||
|
return text.strip()
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
# 设置设备
|
# 设置设备
|
||||||
@@ -31,9 +43,12 @@ def main():
|
|||||||
if text.lower() == 'q':
|
if text.lower() == 'q':
|
||||||
break
|
break
|
||||||
|
|
||||||
|
# 预处理文本
|
||||||
|
processed_text = preprocess_text(text)
|
||||||
|
|
||||||
# 对文本进行编码
|
# 对文本进行编码
|
||||||
encoding = tokenizer(
|
encoding = tokenizer(
|
||||||
text,
|
processed_text,
|
||||||
max_length=128,
|
max_length=128,
|
||||||
padding='max_length',
|
padding='max_length',
|
||||||
truncation=True,
|
truncation=True,
|
||||||
|
|||||||
@@ -2,6 +2,18 @@ import torch
|
|||||||
from transformers import GPT2ForSequenceClassification, BertTokenizer
|
from transformers import GPT2ForSequenceClassification, BertTokenizer
|
||||||
from peft import PeftModel
|
from peft import PeftModel
|
||||||
import os
|
import os
|
||||||
|
import re
|
||||||
|
|
||||||
|
def preprocess_text(text):
|
||||||
|
"""简单的文本预处理"""
|
||||||
|
text = re.sub(r"\{%.+?%\}", " ", text) # 去除 {%xxx%}
|
||||||
|
text = re.sub(r"@.+?( |$)", " ", text) # 去除 @xxx
|
||||||
|
text = re.sub(r"【.+?】", " ", text) # 去除 【xx】
|
||||||
|
text = re.sub(r"\u200b", " ", text) # 去除特殊字符
|
||||||
|
# 删除表情符号
|
||||||
|
text = re.sub(r'[\U0001F600-\U0001F64F\U0001F300-\U0001F5FF\U0001F680-\U0001F6FF\U0001F1E0-\U0001F1FF\U00002600-\U000027BF\U0001f900-\U0001f9ff\U0001f018-\U0001f270\U0000231a-\U0000231b\U0000238d-\U0000238d\U000024c2-\U0001f251]+', '', text)
|
||||||
|
text = re.sub(r"\s+", " ", text) # 多个空格合并
|
||||||
|
return text.strip()
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
# 设置设备
|
# 设置设备
|
||||||
@@ -66,9 +78,12 @@ def main():
|
|||||||
continue
|
continue
|
||||||
|
|
||||||
try:
|
try:
|
||||||
|
# 预处理文本
|
||||||
|
processed_text = preprocess_text(text)
|
||||||
|
|
||||||
# 对文本进行编码
|
# 对文本进行编码
|
||||||
encoding = tokenizer(
|
encoding = tokenizer(
|
||||||
text,
|
processed_text,
|
||||||
max_length=128,
|
max_length=128,
|
||||||
padding='max_length',
|
padding='max_length',
|
||||||
truncation=True,
|
truncation=True,
|
||||||
|
|||||||
Reference in New Issue
Block a user