تقرير
Patent Search Using Triplet Networks Based Fine-Tuned SciBERT
العنوان: | Patent Search Using Triplet Networks Based Fine-Tuned SciBERT |
---|---|
المؤلفون: | Acikalin, Utku Umur, Kutlu, Mucahid |
سنة النشر: | 2022 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Information Retrieval |
الوصف: | 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. Comment: This paper is accepted at the 3rd Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech) 2022 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2207.11497 |
رقم الأكسشن: | edsarx.2207.11497 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |