Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.06093 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916315915091968 |
|---|---|
| author | Sakhrani, Harsh Pervez, Naseela Kumar, Anirudh Ravi Morstatter, Fred Reed, Alexandra Graddy Belz, Andrea |
| author_facet | Sakhrani, Harsh Pervez, Naseela Kumar, Anirudh Ravi Morstatter, Fred Reed, Alexandra Graddy Belz, Andrea |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06093 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Artificial Intuition: Efficient Classification of Scientific Abstracts Sakhrani, Harsh Pervez, Naseela Kumar, Anirudh Ravi Morstatter, Fred Reed, Alexandra Graddy Belz, Andrea Artificial Intelligence 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. |
| title | Artificial Intuition: Efficient Classification of Scientific Abstracts |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2407.06093 |