Improving Patent Mining and Relevance Classification using Transformers

TL;DR

This paper demonstrates how fine-tuning pre-trained transformer models can effectively improve patent relevance classification, reducing workload while maintaining high accuracy in patent analysis.

Contribution

It introduces a novel approach combining state-of-the-art NLP techniques to enhance patent filtering and classification efficiency.

Findings

Improved classification accuracy with transformer models

Reduced manual review workload

Maintained high recall and precision metrics

Abstract

Patent analysis and mining are time-consuming and costly processes for companies, but nevertheless essential if they are willing to remain competitive. To face the overload induced by numerous patents, the idea is to automatically filter them, bringing only few to read to experts. This paper reports a successful application of fine-tuning and retraining on pre-trained deep Natural Language Processing models on patent classification. The solution that we propose combines several state-of-the-art treatments to achieve our goal - decrease the workload while preserving recall and precision metrics.