Patent claim generation by fine-tuning OpenAI GPT-2

Jieh-Sheng Lee*, Jieh Hsiang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

61 Scopus citations


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.

Original languageEnglish
Article number101983
Pages (from-to)1-7
Number of pages7
JournalWorld Patent Information
StatePublished - Sep 2020


Dive into the research topics of 'Patent claim generation by fine-tuning OpenAI GPT-2'. Together they form a unique fingerprint.

Cite this