PHOENIX is a domain-adaptive model based on CLIP/ViT, designed to enhance patent image retrieval capabilities, particularly suitable for retrieving semantically or hierarchically related images rather than exact matches.

Computer VisionSafetensors

This is a Russian patent named entity recognition model based on the spaCy framework, focusing on identifying specific entity types in patent texts.

Natural Language ProcessingSpacyOther

This is a sentence-transformers model fine-tuned from snunlp/KR-Medium-extended, specifically designed for Korean patent text similarity tasks.

Natural Language ProcessingSentence-transformers

Zero-shot image classification model based on OpenCLIP library, suitable for patent image analysis

Computer VisionSafetensors

A model fine-tuned on a small dataset of 16,000 English translations of Korean patents based on Meta-Llama-3-8B-Instruct, for testing purposes only.

Natural Language ProcessingTransformersEnglish

A Chinese patent abstract generation model fine-tuned on qwen1.5-7b, excelling in processing long-text patent specifications and generating concise summaries.

Natural Language ProcessingTransformersChinese

PaECTER is a patent embedding model based on citation-aware Transformer, capable of generating 1024-dimensional dense vector embeddings from patent texts, suitable for patent analysis tasks.

Natural Language ProcessingTransformersEnglish

This is a model based on sentence-transformers that maps sentences and paragraphs into a 384-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

Natural Language ProcessingTransformers

A patent contradiction sentence identification model based on PatentSBERTa, capable of mapping sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

Natural Language ProcessingTransformers

A patent contradiction sentence identification model based on all-MiniLM-L6-v2, capable of mapping sentences and paragraphs into a 384-dimensional dense vector space, suitable for tasks like clustering or semantic search.

Natural Language ProcessingPytorch

A patent parameter sentence recognition model based on all-MiniLM-L6-v2, which maps sentences and paragraphs into a 384-dimensional dense vector space, suitable for tasks like clustering or semantic search.

Natural Language ProcessingPytorch

A Patent Problem and Solution Sentence Identification Model based on PatentSBERTa, which maps sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

Natural Language ProcessingTransformers

A PatentSBERTa-based model for identifying contradictory sentences in patents, capable of mapping sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks like clustering or semantic search.

Natural Language ProcessingTransformers

This model is a fine-tuned T5-small model based on the HUPD dataset, specifically designed for patent text summarization tasks.

Natural Language ProcessingTransformersEnglish

Hybrid deep NLP model using enhanced SBERT for patent distance calculation and classification

Natural Language ProcessingTransformers

Patent text processing model based on BERT-LARGE architecture, optimizing storage efficiency through PCA-compressed embedding dimensions

Natural Language ProcessingTransformersEnglish

ProcBERT is a pre-trained language model specifically optimized for process texts, pre-trained on a large-scale corpus of process texts (including biomedical literature, chemical patents, and cooking recipes), demonstrating outstanding performance in downstream tasks.

Natural Language ProcessingTransformersEnglish

Google's BERT large version model trained on over 100 million global patents, optimized for patent analysis

Natural Language ProcessingTransformersEnglish

This model is a fine-tuned BART-base architecture for patent abstract processing, trained on 7 million patent abstract records, primarily for research reference in patent abstracts.

Natural Language ProcessingTransformers

Hybrid model based on deep NLP, using enhanced SBERT for patent distance calculation and classification

Natural Language ProcessingTransformers