PhysBERT: A Text Embedding Model for Physics Scientific Literature
This addresses the problem of information extraction in physics for researchers, but it is incremental as it adapts existing methods to a new domain.
The authors tackled the challenge of processing physics scientific literature by introducing PhysBERT, a physics-specific text embedding model, which outperformed general-purpose models on physics tasks after pre-training on 1.2 million arXiv papers and fine-tuning.
The specialized language and complex concepts in physics pose significant challenges for information extraction through Natural Language Processing (NLP). Central to effective NLP applications is the text embedding model, which converts text into dense vector representations for efficient information retrieval and semantic analysis. In this work, we introduce PhysBERT, the first physics-specific text embedding model. Pre-trained on a curated corpus of 1.2 million arXiv physics papers and fine-tuned with supervised data, PhysBERT outperforms leading general-purpose models on physics-specific tasks including the effectiveness in fine-tuning for specific physics subdomains.