metadata
model-index:
- name: deberta-v3-large-self-disclosure-detection
results: []
language:
- en
base_model: microsoft/deberta-v3-large
license: mit
tags:
- deberta
- privacy
- self-disclosure identification
- PII
extra_gated_prompt: >
By requesting access to this model, you agree to follow these usage
guidelines:
1. Use the model only for research purposes.
2. Do not redistribute the model or its associated resources without prior
permission from the authors.
3. Clearly acknowledge the original authors in any publications, derivative
works, or other outputs created using this model.
extra_gated_fields:
First Name: text
Last Name: text
Company or Institution: text
Country: country
Specific date: date_picker
I want to use this model for:
type: select
options:
- Research
- Education
- label: Other
value: other
I agree to use this model for research and non-commercial purposes only: checkbox
I agree not to redistribute the model or associated resources without prior permission from the authors: checkbox
I agree to acknowledge the original authors in any publications or derivative works: checkbox
Model Card for deberta-v3-large-self-disclosure-detection
The model is used to detect self-disclosures (personal information) in a sentence. It is a binary token classification task. For example "I am 22 years old and ..." has labels of "["DISCLOSURE", "DISCLOSURE", "DISCLOSURE", "DISCLOSURE", "DISCLOSURE", "O", ...]"
The model is able to detect the following 17 categores: "Age", "Age_Gender", "Appearance", "Education", "Family", "Finance", "Gender", "Health", "Husband_BF", "Location", "Mental_Health", "Occupation", "Pet", "Race_Nationality", "Relationship_Status", "Sexual_Orientation", "Wife_GF".
For more details, please read the paper: Reducing Privacy Risks in Online Self-Disclosures with Language Models .
Accessing this model implies automatic agreement to the following guidelines:
- Only use the model for research purposes.
- No redistribution without the author's agreement.
- Any derivative works created using this model must acknowledge the original author.
Model Description
- Model type: A binary token-classification finetuned model that can detect self-disclosures
- Language(s) (NLP): English
- License: Creative Commons Attribution-NonCommercial
- Finetuned from model: microsoft/deberta-v3-large
Example Code
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-binary"
config = AutoConfig.from_pretrained(model_path,)
label2id = config.label2id
id2label = config.id2label
config.num_labels = 2
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True,)
model = AutoModelForTokenClassification.from_pretrained(model_path, config=config, device_map="cuda:0").eval()
def tokenize_and_align_labels(words):
tokenized_inputs = tokenizer(
words,
padding=False,
is_split_into_words=True,
)
# we use ("O") for all the labels
word_ids = tokenized_inputs.word_ids(0)
previous_word_idx = None
label_ids = []
for word_idx in word_ids:
# Special tokens have a word id that is None. We set the label to -100 so they are automatically
# ignored in the loss function.
if word_idx is None:
label_ids.append(-100)
# We set the label for the first token of each word.
elif word_idx != previous_word_idx:
label_ids.append(label2id["O"])
# For the other tokens in a word, we set the label to -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.",
"We also partnered with news and data providers to add up-to-date information and new visual designs for categories like weather, stocks, sports, news, and maps.",
"My husband and I live in US.",
"I was messing with advanced voice the other day and I was like, 'Oh, I can do this.'",
]
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)
Citation
@article{dou2023reducing,
title={Reducing Privacy Risks in Online Self-Disclosures with Language Models},
author={Dou, Yao and Krsek, Isadora and Naous, Tarek and Kabra, Anubha and Das, Sauvik and Ritter, Alan and Xu, Wei},
journal={arXiv preprint arXiv:2311.09538},
year={2023}
}