model-index:

• name: deberta-v3-large-self-disclosure-detection results: [] language:
• en base_model: microsoft/deberta-v3-large license: mit tags:
• deberta
• privacy
• 自我披露识别
• 个人身份信息

模型卡片：deberta-v3-large-self-disclosure-detection

该模型用于检测句子中的自我披露（个人信息）。这是一个多类别的标记分类任务，类似于IOB2格式的命名实体识别（NER）。
例如："I am 22 years old and ..." 的标签为 ["B-Age", "I-Age", "I-Age", "I-Age", "I-Age", "O", ...]

模型能够识别以下17个类别：
"年龄", "年龄_性别", "外貌", "教育", "家庭", "财务", "性别", "健康", "丈夫_男友",
"位置", "心理健康", "职业", "宠物", "种族_国籍", "关系状态", "性取向", "妻子_女友"。

更多细节请参阅论文：利用语言模型降低在线自我披露的隐私风险。

使用本模型即自动同意以下准则：

1. 仅限研究用途。
2. 未经作者同意不得二次分发。
3. 任何基于本模型的衍生作品必须注明原作者。

模型描述

• 模型类型： 微调模型，可检测17类自我披露信息。
• 支持语言： 英语
• 许可协议： 知识共享-非商业性使用
• 基础模型： microsoft/deberta-v3-large

示例代码

import torch
from torch.utils.data import DataLoader, Dataset

import datasets
from datasets import ClassLabel, load_dataset

from transformers import AutoModelForTokenClassification, AutoTokenizer, AutoConfig, DataCollatorForTokenClassification

model_path = "douy/deberta-v3-large-self-disclosure-detection"

config = AutoConfig.from_pretrained(model_path,)

tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True,)

model = AutoModelForTokenClassification.from_pretrained(model_path,config=config,device_map="cuda:0").eval()

label2id = config.label2id
id2label = config.id2label


def tokenize_and_align_labels(words):
    tokenized_inputs = tokenizer(
                words,
                padding=False,
                is_split_into_words=True,
            )

    # 所有标签初始设为("O")
    word_ids = tokenized_inputs.word_ids(0)
    previous_word_idx = None
    label_ids = []
    for word_idx in word_ids:
        # 特殊标记的word_id为None，标签设为-100（损失函数自动忽略）
        if word_idx is None:
            label_ids.append(-100)
        # 每个单词的首个标记设置标签
        elif word_idx != previous_word_idx:
            label_ids.append(label2id["O"])
        # 单词的其他标记标签设为-100
        else:
            label_ids.append(-100)
        previous_word_idx = word_idx
    tokenized_inputs["labels"] = label_ids
    return tokenized_inputs

class DisclosureDataset(Dataset):
    def __init__(self, inputs, tokenizer, tokenize_and_align_labels_function):
        self.inputs = inputs
        self.tokenizer = tokenizer
        self.tokenize_and_align_labels_function = tokenize_and_align_labels_function

    def __len__(self):
        return len(self.inputs)

    def __getitem__(self, idx):
        words = self.inputs[idx]
        tokenized_inputs = self.tokenize_and_align_labels_function(words)
        return tokenized_inputs
    
    
sentences = [
    "I am a 23-year-old who is currently going through the last leg of undergraduate school.",
    "My husband and I live in US.",
]

inputs = [sentence.split() for sentence in sentences]

data_collator = DataCollatorForTokenClassification(tokenizer)

dataset = DisclosureDataset(inputs, tokenizer, tokenize_and_align_labels)

dataloader = DataLoader(dataset, collate_fn=data_collator, batch_size=2)

total_predictions = []
for step, batch in enumerate(dataloader):
    batch = {k: v.to(model.device) for k, v in batch.items()}
    with torch.inference_mode():
        outputs = model(**batch)
    predictions = outputs.logits.argmax(-1)
    labels = batch["labels"]

    predictions = predictions.cpu().tolist()
    labels = labels.cpu().tolist()

    true_predictions = []
    for i, label in enumerate(labels):
        true_pred = []
        for j, m in enumerate(label):
            if m != -100:
                true_pred.append(id2label[predictions[i][j]])
        true_predictions.append(true_pred)
    total_predictions.extend(true_predictions)
    

for word, pred in zip(inputs, total_predictions):
    for w, p in zip(word, pred):
        print(w, p)

评估结果

模型取得65.71的部分跨度F1值，优于GPT-4提示方法（57.68 F1）。各类别详细性能参见论文。

引用文献

@article{dou2023reducing,
  title={利用语言模型降低在线自我披露的隐私风险},
  author={Dou, Yao and Krsek, Isadora and Naous, Tarek and Kabra, Anubha and Das, Sauvik and Ritter, Alan and Xu, Wei},
  journal={arXiv预印本 arXiv:2311.09538},
  year={2023}
}