In this paper, we propose a novel method for the prior-art search task. We fine-tune SciBERT transformer model using Triplet Network approach, allowing us to represent each patent with a fixed-size vector. This also enables us to conduct efficient vector similarity computations to rank patents in query time. In our experiments, we show that our proposed method outperforms baseline methods.
Cite
@article{arxiv.2207.11497,
title = {Patent Search Using Triplet Networks Based Fine-Tuned SciBERT},
author = {Utku Umur Acikalin and Mucahid Kutlu},
journal= {arXiv preprint arXiv:2207.11497},
year = {2022}
}
Comments
This paper is accepted at the 3rd Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech) 2022