Yerim Oh — accepted AI-conference papers

2025

Incorporating Domain Knowledge into Materials Tokenization

Yerim Oh, Jun-Hyung Park, Junho Kim, SungHo Kim, SangKeun Lee

ACL 2025long

While language models are increasingly utilized in materials science, typical models rely on frequency-centric tokenization methods originally developed for natural language processing. However, these methods frequently produce excessive fragmentation and semantic loss, failing to maintain the struc…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science

Junho Kim, Yeachan Kim, Jun-Hyung Park, Yerim Oh, Suho Kim, SangKeun Lee

EMNLP 2024finding

We introduce a novel continued pre-training method, MELT (MatEriaLs-aware continued pre-Training), specifically designed to efficiently adapt the pre-trained language models (PLMs) for materials science. Unlike previous adaptation strategies that solely focus on constructing domain-specific corpus,…

Cited by 2 Source ↗PDF ↗Scholar ↗