Summary of Cheap Ways Of Extracting Clinical Markers From Texts, by Anastasia Sandu et al.
Cheap Ways of Extracting Clinical Markers from Texts
by Anastasia Sandu, Teodor Mihailescu, Sergiu Nisioi
First submitted to arxiv on: 17 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 This paper presents the UniBuc Archaeology team’s contribution to CLPsych’s 2024 Shared Task, which involves identifying textual evidence supporting assigned suicide risk levels. The task requires extracting relevant highlights and summarizing evidence into a synthesis. The research evaluates Large Language Models (LLMs) as alternatives to traditional methods that are more memory- and resource-efficient. One approach employs a machine learning pipeline using tf-idf vectorization and logistic regression for highlight extraction, while the other uses LLMs to generate summaries guided by chain-of-thought to provide clinical markers. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding clues in text that help predict suicide risk levels. The researchers tried two different methods: one was like a detective searching for important phrases and summarizing them, while the other used big language models to generate long sequences of text indicating key signs. They wanted to see if these newer models could do the job more efficiently than traditional approaches. |
Keywords
* Artificial intelligence * Logistic regression * Machine learning * Tf idf * Vectorization
