MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling
This work addresses the need for domain-specific NLP evaluation in materials science, offering a benchmark and improved methods for researchers in that field, though it is incremental as it builds on existing BERT-based approaches.
The authors tackled the problem of evaluating NLP models on materials science text by creating the MatSci-NLP benchmark with seven tasks, and found that models pretrained on scientific text, especially MatBERT, outperform general BERT, with their proposed text-to-schema method achieving better results than traditional fine-tuning in low-resource settings.
We present MatSci-NLP, a natural language benchmark for evaluating the performance of natural language processing (NLP) models on materials science text. We construct the benchmark from publicly available materials science text data to encompass seven different NLP tasks, including conventional NLP tasks like named entity recognition and relation classification, as well as NLP tasks specific to materials science, such as synthesis action retrieval which relates to creating synthesis procedures for materials. We study various BERT-based models pretrained on different scientific text corpora on MatSci-NLP to understand the impact of pretraining strategies on understanding materials science text. Given the scarcity of high-quality annotated data in the materials science domain, we perform our fine-tuning experiments with limited training data to encourage the generalize across MatSci-NLP tasks. Our experiments in this low-resource training setting show that language models pretrained on scientific text outperform BERT trained on general text. MatBERT, a model pretrained specifically on materials science journals, generally performs best for most tasks. Moreover, we propose a unified text-to-schema for multitask learning on \benchmark and compare its performance with traditional fine-tuning methods. In our analysis of different training methods, we find that our proposed text-to-schema methods inspired by question-answering consistently outperform single and multitask NLP fine-tuning methods. The code and datasets are publicly available at \url{https://github.com/BangLab-UdeM-Mila/NLP4MatSci-ACL23}.