English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this work, we focus on fine-tuning an OpenAI GPT-2 pre-trained model forgenerating patent claims. GPT-2 has demonstrated impressive efficacy ofpre-trained language models on various tasks, particularly coherent textgeneration. Patent claim language itself has rarely been explored in the pastand poses a unique challenge. We are motivated to generate coherent patentclaims automatically so that augmented inventing might be viable someday. Inour implementation, we identified a unique language structure in patent claimsand leveraged its implicit human annotations. We investigated the fine-tuningprocess by probing the first 100 steps and observing the generated text at eachstep. Based on both conditional and unconditional random sampling, we analyzethe overall quality of generated patent claims. Our contributions include: (1)being the first to generate patent claims by machines and being the first toapply GPT-2 to patent claim generation, (2) providing various experimentresults for qualitative analysis and future research, (3) proposing a newsampling approach for text generation, and (4) building an e-mail bot forfuture researchers to explore the fine-tuned GPT-2 model further.

Patent Claim Generation by Fine-Tuning OpenAI GPT-2