Semantic Similarity Matching for Patent Documents Using Ensemble BERT-related Model and Novel Text Processing Method

TL;DR

This paper proposes an ensemble of four BERT-based models combined with a novel text preprocessing technique to improve semantic similarity assessment in patent documents, specifically aiding Cooperative Patent Classification tasks.

Contribution

It introduces a novel ensemble approach with weighted averaging and a new text preprocessing method tailored for patent documents, enhancing semantic similarity accuracy.

Findings

Ensemble model outperforms individual BERT models in accuracy.

Novel text processing improves semantic relationship capture.

Effective on U.S. Patent Phrase to Phrase Matching dataset.

Abstract

In the realm of patent document analysis, assessing semantic similarity between phrases presents a significant challenge, notably amplifying the inherent complexities of Cooperative Patent Classification (CPC) research. Firstly, this study addresses these challenges, recognizing early CPC work while acknowledging past struggles with language barriers and document intricacy. Secondly, it underscores the persisting difficulties of CPC research. To overcome these challenges and bolster the CPC system, This paper presents two key innovations. Firstly, it introduces an ensemble approach that incorporates four BERT-related models, enhancing semantic similarity accuracy through weighted averaging. Secondly, a novel text preprocessing method tailored for patent documents is introduced, featuring a distinctive input structure with token scoring that aids in capturing semantic relationships during CPC context training, utilizing BCELoss. Our experimental findings conclusively establish the effectiveness of both our Ensemble Model and novel text processing strategies when deployed on the U.S. Patent Phrase to Phrase Matching dataset.