Skip to main content

Current Duke Appointments & Affiliations


Recent Scholarly Works


MATVIX: Multimodal Information Extraction from Visually Rich Articles

Conference Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics Human Language Technologies Long Papers Naacl Hlt 2025 · January 1, 2025 Multimodal information extraction (MIE) is crucial for scientific literature, where valuable data is often spread across text, figures, and tables. In materials science, extracting structured information from research articles can accelerate the discovery ... Full text Cite

How Well Do Large Language Models Understand Tables in Materials Science?

Journal article Integrating Materials and Manufacturing Innovation · September 1, 2024 Advances in materials science require leveraging past findings and data from the vast published literature. While some materials data repositories are being built, they typically rely on newly created data in narrow domains because extracting detailed data ... Full text Cite

Approximating CKY with Transformers

Conference Findings of the Association for Computational Linguistics: EMNLP 2023 · 2023 Full text Cite
View All Scholarly Works