https://scholars.lib.ntu.edu.tw/handle/123456789/581372
標題: | Patent claim generation by fine-tuning OpenAI GPT-2 | 作者: | Lee J.-S Hsiang J. JIEH HSIANG |
公開日期: | 2020 | 卷: | 62 | 來源出版物: | World Patent Information | 摘要: | In this work, we focus on fine-tuning an OpenAI GPT-2 pre-trained model for generating patent claims. GPT-2 has demonstrated impressive efficacy of pre-trained language models on various tasks, particularly coherent text generation. Patent claim language itself has rarely been explored in the past and poses a unique challenge. We are motivated to generate coherent patent claims automatically so that augmented inventing might be viable someday. In our implementation, we identified a unique language structure in patent claims and leveraged its implicit human annotations. We investigated the fine-tuning process by probing the first 100 steps and observing the generated text at each step. Based on both conditional and unconditional random sampling, we analyze the overall quality of generated patent claims. Our contributions include: (1) being the first to generate patent claims by machines and being the first to apply GPT-2 to patent claim generation, (2) providing various experiment results for qualitative analysis and future research, (3) proposing a new sampling approach for text generation, and (4) publishing our fine-tuned GPT-2 model and sample code for future researchers to run on Colab. ? 2020 Elsevier Ltd |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089462589&doi=10.1016%2fj.wpi.2020.101983&partnerID=40&md5=18a84e633b93495db4e791a68398c3a6 https://scholars.lib.ntu.edu.tw/handle/123456789/581372 |
ISSN: | 01722190 | DOI: | 10.1016/j.wpi.2020.101983 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。