AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

CAPP-130: A Corpus of Chinese Application Privacy Policy Summarization and Interpretation

Pengyun Zhu, Long Wen, Jinfei Liu, Feng Xue, Jian Lou, Zhibo Wang, Kui Ren

NeurIPS 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use RoBERTa instead of Bert as encoder for topic screeningTCSI-pp information extraction · CAPP-130 topic-multiMicro-F1: 0.802 -> 0.819Improved
use RoBERTa instead of SBERT as encoder for topic screeningTCSI-pp information extraction · CAPP-130 topic-multiMicro-F1: 0.781 -> 0.819Improved
use RoBERTa instead of PERT for important-binary screeningTCSI-pp information extraction · CAPP-130 important-binaryMacro-F1: 0.897 -> 0.899Improved
use RoBERTa instead of PERT for risk-binary screeningTCSI-pp information extraction · CAPP-130 risk-binaryMicro-F1: 0.922 -> 0.920No clear effect
use RoBERTa instead of Bert for risk-binary screeningTCSI-pp information extraction · CAPP-130 risk-binaryMacro-F1: 0.719 -> 0.711No clear effect
use mT5 instead of Bert2gpt for sentence rewritingTCSI-pp-zh rewriting model · CAPP-130 rewritingCarburacy: 0.764 -> 0.833Improved
use mT5 instead of ERNIE2gpt for sentence rewritingTCSI-pp-zh rewriting model · CAPP-130 rewritingROUGE-1: 0.623 -> 0.753Improved
use mT5 instead of Bert2gpt for sentence rewritingTCSI-pp-zh rewriting model · CAPP-130 rewritingROUGE-2: 0.574 -> 0.609Improved
use TCSI-pp-zh instead of GPT-4 summariesprivacy policy summarization · Readability surveyshare of votes: 42.13% -> 46.23%Improved
use TCSI-pp-zh instead of Llama2-Chinese summariesprivacy policy summarization · Readability surveyshare of votes: 6.39% -> 46.23%Improved
data usage topic classified with RoBERTa/mBERTfine-grained screening · CAPP-130 topicsF1Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy