88 citations · 101 across the 4 of their papers we have counts for
5 papers
Prior Art Search and Reranking for Generated Patent Text
Jieh-Sheng Lee, Jieh Hsiang
Generative models, such as GPT-2, have demonstrated impressive results recently. A fundamental question we'd like to address is: where did the generated text come from? This work i…
PatentTransformer-2: Controlling Patent Text Generation by Structural Metadata
Jieh-Sheng Lee, Jieh Hsiang
PatentTransformer is our codename for patent text generation based on Transformer-based models. Our goal is "Augmented Inventing." In this second version, we leverage more of the s…
Measuring Patent Claim Generation by Span Relevancy
Jieh-Sheng Lee, Jieh Hsiang
Our goal of patent claim generation is to realize "augmented inventing" for inventors by leveraging latest Deep Learning techniques. We envision the possibility of building an "aut…
Patent Claim Generation by Fine-Tuning OpenAI GPT-2
Jieh-Sheng Lee, Jieh Hsiang
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 v…
PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT Model
Jieh-Sheng Lee, Jieh Hsiang
In this work we focus on fine-tuning a pre-trained BERT model and applying it to patent classification. When applied to large datasets of over two millions patents, our approach ou…