Summary of Aspirinsum: An Aspect-based Utility-preserved De-identification Summarization Framework, by Ya-lun Li
AspirinSum: an Aspect-based utility-preserved de-identification Summarization framework
by Ya-Lun Li
First submitted to arxiv on: 20 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this research paper, a new framework called AspirinSum is proposed to efficiently de-identify personal sensitive text data without human annotation. The goal is to develop a generalizable method that can be easily adapted to specific domains like healthcare or education. Currently, most methods rely on human annotation or predefined categories, which are not effective for adapting to different domains. AspirinSum leverages existing expert knowledge by learning to align aspects from comment data and then summarizes personal sensitive documents by extracting relevant sub-sentences and replacing them with similar ones. This approach aims to create a de-identified text dataset that can be used in data publishing, ultimately benefiting downstream tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a new way to make private information public without putting people’s privacy at risk. Right now, it’s hard to share medical or educational texts because they contain personal details. Researchers want to find a way to remove these sensitive parts without needing human help. They’ve tried doing this for images and tables before, but not for text. This new method is called AspirinSum and it works by using expert knowledge from comments to summarize private documents and replace the sensitive parts with similar ones that are safe to share. |
