Structured information extraction from complex scientific text with fine-tuned large language models

TL;DR

This paper introduces a fine-tuned GPT-3 based method for extracting structured scientific information from complex texts, demonstrating high accuracy across multiple chemistry-related tasks and providing an accessible approach for building large knowledge databases.

Contribution

It presents a simple, flexible sequence-to-sequence fine-tuning approach using GPT-3 for joint entity and relation extraction in scientific texts, applicable across multiple tasks.

Findings

Accurately extracts complex scientific data from unstructured text

Works across sentences and passages for comprehensive information gathering

Enables creation of large structured knowledge databases

Abstract

Intelligently extracting and linking complex scientific information from unstructured text is a challenging endeavor particularly for those inexperienced with natural language processing. Here, we present a simple sequence-to-sequence approach to joint named entity recognition and relation extraction for complex hierarchical information in scientific text. The approach leverages a pre-trained large language model (LLM), GPT-3, that is fine-tuned on approximately 500 pairs of prompts (inputs) and completions (outputs). Information is extracted either from single sentences or across sentences in abstracts/passages, and the output can be returned as simple English sentences or a more structured format, such as a list of JSON objects. We demonstrate that LLMs trained in this way are capable of accurately extracting useful records of complex scientific knowledge for three representative tasks in materials chemistry: linking dopants with their host materials, cataloging metal-organic frameworks, and general chemistry/phase/morphology/application information extraction. This approach represents a simple, accessible, and highly-flexible route to obtaining large databases of structured knowledge extracted from unstructured text. An online demo is available at http://www.matscholar.com/info-extraction.