Symbol-based entity marker highlighting for enhanced text mining in materials science with generative AI
This work addresses the challenge of data extraction for materials science researchers, offering incremental improvements in entity recognition and data structuring.
The paper tackles the problem of converting unstructured scientific text into structured data by proposing a hybrid text-mining framework that integrates multi-step and direct methods, resulting in up to 58% improvement in entity-level F1 score and up to 83% improvement in relation-level F1 score compared to direct approaches.
The construction of experimental datasets is essential for expanding the scope of data-driven scientific discovery. Recent advances in natural language processing (NLP) have facilitated automatic extraction of structured data from unstructured scientific literature. While existing approaches-multi-step and direct methods-offer valuable capabilities, they also come with limitations when applied independently. Here, we propose a novel hybrid text-mining framework that integrates the advantages of both methods to convert unstructured scientific text into structured data. Our approach first transforms raw text into entity-recognized text, and subsequently into structured form. Furthermore, beyond the overall data structuring framework, we also enhance entity recognition performance by introducing an entity marker-a simple yet effective technique that uses symbolic annotations to highlight target entities. Specifically, our entity marker-based hybrid approach not only consistently outperforms previous entity recognition approaches across three benchmark datasets (MatScholar, SOFC, and SOFC slot NER) but also improve the quality of final structured data-yielding up to a 58% improvement in entity-level F1 score and up to 83% improvement in relation-level F1 score compared to direct approach.