Artificial Intuition: Efficient Classification of Scientific Abstracts

It is desirable to coarsely classify short scientific texts, such as grant or publication abstracts, for strategic insight or research portfolio management. These texts efficiently transmit dense information to experts possessing a rich body of knowledge to aid interpretation. Yet this task is remar...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-07
Main Authors: Sakhrani, Harsh, Pervez, Naseela, Anirudh Ravi Kumar, Morstatter, Fred, Alexandra Graddy Reed, Belz, Andrea
Format: Article
Language:English
Subjects:
Aeronautics
Knowledge representation
Large language models
Performance measurement
Texts
Workflow
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is desirable to coarsely classify short scientific texts, such as grant or publication abstracts, for strategic insight or research portfolio management. These texts efficiently transmit dense information to experts possessing a rich body of knowledge to aid interpretation. Yet this task is remarkably difficult to automate because of brevity and the absence of context. To address this gap, we have developed a novel approach to generate and appropriately assign coarse domain-specific labels. We show that a Large Language Model (LLM) can provide metadata essential to the task, in a process akin to the augmentation of supplemental knowledge representing human intuition, and propose a workflow. As a pilot study, we use a corpus of award abstracts from the National Aeronautics and Space Administration (NASA). We develop new assessment tools in concert with established performance metrics.
ISSN:2331-8422