PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT Model
This work addresses patent classification for researchers and practitioners, showing that patent claims alone are sufficient, which is incremental but with practical implications.
The authors tackled patent classification by fine-tuning a pre-trained BERT model on a large dataset of over two million patents, achieving state-of-the-art performance that outperforms CNN-based methods.
In this work we focus on fine-tuning a pre-trained BERT model and applying it to patent classification. When applied to large datasets of over two millions patents, our approach outperforms the state of the art by an approach using CNN with word embeddings. In addition, we focus on patent claims without other parts in patent documents. Our contributions include: (1) a new state-of-the-art method based on pre-trained BERT model and fine-tuning for patent classification, (2) a large dataset USPTO-3M at the CPC subclass level with SQL statements that can be used by future researchers, (3) showing that patent claims alone are sufficient for classification task, in contrast to conventional wisdom.