This interdisciplinary survey aims to serve as a comprehensive resource for researchers and practitioners who work at the intersection of NLP, Multimodal AI, and patent analysis, as well as patent offices to build effi- cient patent systems.
-
USPTO-2M - Deeppatent: patent classification with convolutional neural networks and word embedding
-
BIGPATENT - BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization
-
USPTO-3M - Patent Classification by Fine-Tuning BERT Language Model
-
PatentMatch - Patentmatch: A dataset for matching patent claims & prior art
-
DeepPatent - DeepPatent: Large scale patent drawing recognition and retrieval
-
DeepPatent2 - DeepPatent2: A Large-Scale Benchmarking Corpus for Technical Drawing Understanding
-
IMPACT - MPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents
- Automated Patent Classification Using Word Embedding
- An lstm approach to patent classification based on fixed hierarchy vectors
- Learning patent speak: Investigating domain-specific word embeddings
- Classifying patent applications with ensemble methods
- Domain-specific word embeddings for patent classification
- Patent classification by fine-tuning bert language model
- Linguistically informed masking for representation learning in the patent do- main
- Deep learning based pipeline with multichannel inputs for patent classification
- Patentnet: multi-label classification of patent documents using deep learning based language understanding
- Automated single-label patent classification using ensemble clas- sifiers
- Classification of visualization types and perspectives in patents
- An ensemble framework for patent classification
- A deep nlp based hybrid model for patent distance and classification using augmented sbert