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 2636 of 36 papers

TitleStatusHype
Multi label classification of Artificial Intelligence related patents using Modified D2SBERT and Sentence Attention mechanism0
Patents Phrase to Phrase Semantic Matching Dataset0
Research on feature fusion and multimodal patent text based on graph attention network0
Retrouver l'inventeur-auteur : la levée d'homonymies d'autorat entre les brevets et les publications scientifiques0
A Survey on Sentence Embedding Models Performance for Patent AnalysisCode0
A Novel Patent Similarity Measurement Methodology: Semantic Distance and Technological DistanceCode0
Event-based Dynamic Graph Representation Learning for Patent Application Trend PredictionCode0
Adaptive Taxonomy Learning and Historical Patterns Modelling for Patent ClassificationCode0
ClusterDataSplit: Exploring Challenging Clustering-Based Data Splits for Model Performance EvaluationCode0
PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT ModelCode0
Technological taxonomies for hypernym and hyponym retrieval in patent textsCode0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.