Summary of Disease Entity Recognition and Normalization Is Improved with Large Language Model Derived Synthetic Normalized Mentions, by Kuleen Sasse et al.
Disease Entity Recognition and Normalization is Improved with Large Language Model Derived Synthetic Normalized Mentions
by Kuleen Sasse, Shinjitha Vadlakonda, Richard E. Kennedy, John D. Osborne
First submitted to arxiv on: 10 Oct 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 proposes a novel approach for improving machine learning methods for clinical named entity recognition and entity normalization systems by leveraging both labeled corpora and Knowledge Graphs (KGs). The authors identify a significant challenge: infrequently occurring concepts may have few mentions in training corpora, which can hinder performance in tasks like Disease Entity Recognition (DER) and Disease Entity Normalization (DEN). To address this issue, the paper suggests generating synthetic training examples using Large Language Models (LLMs), which could increase the availability of high-quality training data for these information extraction tasks. The proposed approach has the potential to improve model performance and expand its applicability to a broader range of diseases. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computers better at understanding medical information. Right now, computer programs can struggle with recognizing and organizing complex medical terms. One reason for this is that there are many rare or unknown medical conditions, which don’t have much data available for training the computer models. The authors suggest a creative solution to overcome this limitation: using large language models to generate fake training examples based on what we already know about diseases. This could help improve the accuracy and effectiveness of these computer programs in processing medical information. |
Keywords
» Artificial intelligence » Machine learning » Named entity recognition
