paper-with-me

Papers

PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT Model

2019-05-14 · 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 outperforms the state of the art by an approach using CNN with word embeddings. In addition, we focus on patent claims without other parts in patent documents. Our contributions include: (1) a new state-of-the-art method based on pre-trained BERT model and fine-tuning for patent classification, (2) a large dataset USPTO-3M at the CPC subclass level with SQL statements that can be used by future researchers, (3) showing that patent claims alone are sufficient for classification task, in contrast to conventional wisdom.

📄 PDF Abstract BibTeX arXiv:1906.02124

Code (1)

jiehsheng/PatentBERT 공식 구현

Tasks

ClassificationGeneral ClassificationMulti-Label Text ClassificationPatent classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Patent Language Model Pretraining with ModernBERT

2025-09-18 · Amirhossein Yousefiramandi, Ciaran Cooney arxiv

Transformer-based language models such as BERT have become foundational in NLP, yet their performance degrades in specialized domains like patents, which contain long, technical, and legally structured text. Prior approa…

Measuring Patent Claim Generation by Span Relevancy

2019-08-26 · 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 "auto-complete" function for inventors to co…

Language ModellingNatural Language InferenceText Generation

Universal Language Model Fine-tuning for Patent Classification

2018-12-01 · ALTA 2018 12 · Jason Hepburn

This paper describes the methods used for the 2018 ALTA Shared Task. The task this year was to automatically classify Australian patents into their main International Patent Classification section. Our final submission u…

ClassificationGeneral ClassificationLanguage ModelingLanguage Modelling+3

Improving Patent Mining and Relevance Classification using Transformers

2021-05-09 · Théo Ding, Walter Vermeiren, Sylvie Ranwez, Binbin Xu

Patent analysis and mining are time-consuming and costly processes for companies, but nevertheless essential if they are willing to remain competitive. To face the overload induced by numerous patents, the idea is to aut…

ClassificationGeneral ClassificationPatent classification

Patent Claim Generation by Fine-Tuning OpenAI GPT-2

2019-07-01 · 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 various tasks, particularly coherent text…

Text Generation