Artificial Intuition: Efficient Classification of Scientific Abstracts
- URL: http://arxiv.org/abs/2407.06093v1
- Date: Mon, 8 Jul 2024 16:34:47 GMT
- Title: Artificial Intuition: Efficient Classification of Scientific Abstracts
- Authors: Harsh Sakhrani, Naseela Pervez, Anirudh Ravi Kumar, Fred Morstatter, Alexandra Graddy Reed, Andrea Belz,
- Abstract summary: Short scientific texts efficiently transmit dense information to experts possessing a rich body of knowledge to aid interpretation.
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.
- Score: 42.299140272218274
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature [80.49349719239584]
We present SciRIFF (Scientific Resource for Instruction-Following and Finetuning), a dataset of 137K instruction-following demonstrations for 54 tasks.
SciRIFF is the first dataset focused on extracting and synthesizing information from research literature across a wide range of scientific fields.
arXiv Detail & Related papers (2024-06-10T21:22:08Z) - Large Language Models for Scientific Information Extraction: An
Empirical Study for Virology [0.0]
We champion the use of structured and semantic content representation of discourse-based scholarly communication.
Inspired by tools like Wikipedia infoboxes or structured Amazon product descriptions, we develop an automated approach to produce structured scholarly contribution summaries.
Our results show that finetuned FLAN-T5 with 1000x fewer parameters than the state-of-the-art GPT-davinci is competitive for the task.
arXiv Detail & Related papers (2024-01-18T15:04:55Z) - An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models [55.01592097059969]
Supervised finetuning on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities.
Active learning is effective in identifying useful subsets of samples to annotate from an unlabeled pool.
We propose using experimental design to circumvent the computational bottlenecks of active learning.
arXiv Detail & Related papers (2024-01-12T16:56:54Z) - Leveraging Knowledge Graphs for Orphan Entity Allocation in Resume
Processing [1.3654846342364308]
This research presents a novel approach for orphan entity allocation in resume processing using knowledge graphs.
The aim is to automate and enhance the efficiency of the job screening process by successfully bucketing orphan entities within resumes.
arXiv Detail & Related papers (2023-10-21T19:10:30Z) - Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction [104.29108668347727]
This paper proposes an innovative knowledge graph generation approach that leverages the potential of the latest generative large language models.
The approach is conveyed in a pipeline that comprises novel iterative zero-shot and external knowledge-agnostic strategies.
We claim that our proposal is a suitable solution for scalable and versatile knowledge graph construction and may be applied to different and novel contexts.
arXiv Detail & Related papers (2023-07-03T16:01:45Z) - Pre-training Multi-task Contrastive Learning Models for Scientific
Literature Understanding [52.723297744257536]
Pre-trained language models (LMs) have shown effectiveness in scientific literature understanding tasks.
We propose a multi-task contrastive learning framework, SciMult, to facilitate common knowledge sharing across different literature understanding tasks.
arXiv Detail & Related papers (2023-05-23T16:47:22Z) - Making Science Simple: Corpora for the Lay Summarisation of Scientific
Literature [21.440724685950443]
We present two novel lay summarisation datasets, PLOS (large-scale) and eLife (medium-scale)
We provide a thorough characterisation of our lay summaries, highlighting differing levels of readability and abstractiveness between datasets.
arXiv Detail & Related papers (2022-10-18T15:28:30Z) - CitationIE: Leveraging the Citation Graph for Scientific Information
Extraction [89.33938657493765]
We use the citation graph of referential links between citing and cited papers.
We observe a sizable improvement in end-to-end information extraction over the state-of-the-art.
arXiv Detail & Related papers (2021-06-03T03:00:12Z) - Generating Knowledge Graphs by Employing Natural Language Processing and
Machine Learning Techniques within the Scholarly Domain [1.9004296236396943]
We present a new architecture that takes advantage of Natural Language Processing and Machine Learning methods for extracting entities and relationships from research publications.
Within this research work, we i) tackle the challenge of knowledge extraction by employing several state-of-the-art Natural Language Processing and Text Mining tools.
We generated a scientific knowledge graph including 109,105 triples, extracted from 26,827 abstracts of papers within the Semantic Web domain.
arXiv Detail & Related papers (2020-10-28T08:31:40Z) - The SOFC-Exp Corpus and Neural Approaches to Information Extraction in
the Materials Science Domain [11.085048329202335]
We develop an annotation scheme for marking information on experiments related to solid oxide fuel cells in scientific publications.
A corpus and an inter-annotator agreement study demonstrate the complexity of the suggested named entity recognition.
We present strong neural-network based models for a variety of tasks that can be addressed on the basis of our new data set.
arXiv Detail & Related papers (2020-06-04T17:49:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.