Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Datasets

AmazUtah_NLP at SemEval-2024 Task 9: A MultiChoice Question Answering System for Commonsense Defying Reasoning


View a PDF of the paper titled Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Datasets, by Satanu Ghosh and 5 other authors

View PDF
HTML (experimental)

Abstract:We explore the ability of GPT-4 to perform ad-hoc schema based information extraction from scientific literature. We assess specifically whether it can, with a basic prompting approach, replicate two existing material science datasets, given the manuscripts from which they were originally manually extracted. We employ materials scientists to perform a detailed manual error analysis to assess where the model struggles to faithfully extract the desired information, and draw on their insights to suggest research directions to address this broadly important task.

Submission history

From: Satanu Ghosh [view email]
[v1]
Sat, 8 Jun 2024 04:24:16 UTC (3,076 KB)
[v2]
Wed, 11 Dec 2024 19:28:47 UTC (3,077 KB)



Source link
lol

By stp2y

Leave a Reply

Your email address will not be published. Required fields are marked *

No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.