Litcius/Paper detail

Annotating Materials Science Text: A Semi-automated Approach for Crafting Outputs with Gemini Pro

Hasan M. Sayeed, Trupti Mohanty, Taylor D. Sparks

2024Integrating materials and manufacturing innovation13 citationsDOIOpen Access PDF

Abstract

Recent advancements in large language models (LLMs) have paved the way for automated information extraction in the materials science domain. However, fine-tuning these models, crucial for effective machine learning pipelines in materials science, is hindered by a lack of pre-annotated data. Manual annotation, a laborious process, exacerbates the challenge. To address this, we introduce a tailored semi-automated annotation process, using Google’s Gemini Pro language model. Our approach focuses on two key tasks: extracting information in structured JSON format and generating abstractive summaries from materials science texts. The collaborative process, a symbiotic effort between human annotators and the LLM, driven by structured prompts and user-guided examples, enhances the annotation quality and augments the LLM’s capacity to comprehend materials science intricacies. Importantly, it streamlines human annotation efforts by leveraging the LLM’s proficient starting point.

Topics & Concepts

Computer scienceAnnotationProcess (computing)JSONKey (lock)Domain (mathematical analysis)Point (geometry)Data scienceInformation retrievalArtificial intelligenceWorld Wide WebProgramming languageMathematicsGeometryMathematical analysisComputer securityMachine Learning in Materials ScienceTopic ModelingNatural Language Processing Techniques