SOTAVerified

Patent classification

Patent reviewers usually are responsible to classify the patent applications, i.e., they assign the design codes. This is time-consuming due to the numerous classification codes. For instance, the U.S. design patent system has 33 classes which are further divided into subclasses. Given that design patents include both titles and visual content, the goal of the experiment is patent classification by integrating titles, captions, and images. Although a single design patent can be associated with multiple design codes, we focus on the primary classification—solving the task as a multi-class classification problem.

Papers

Showing 110 of 36 papers

TitleStatusHype
PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERTCode1
IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design PatentsCode1
Technological taxonomies for hypernym and hyponym retrieval in patent textsCode0
A Novel Patent Similarity Measurement Methodology: Semantic Distance and Technological DistanceCode0
A Survey on Sentence Embedding Models Performance for Patent AnalysisCode0
Adaptive Taxonomy Learning and Historical Patterns Modelling for Patent ClassificationCode0
Event-based Dynamic Graph Representation Learning for Patent Application Trend PredictionCode0
PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT ModelCode0
ClusterDataSplit: Exploring Challenging Clustering-Based Data Splits for Model Performance EvaluationCode0
Automated Single-Label Patent Classification using Ensemble Classifiers0
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.