
PaECTER is a novel document-level encoder specifically designed for patents, outperforming existing models in similarity tasks by incorporating citation information. The authors introduce contrastive learning to enhance similarity detection in patent texts.


coremsg

PaECTER-Patent-level-Representation-Learning-using-Citation-informed-Transformers


PaECTER: Patent-level Representation Learning using Citation-informed Transformers


title_rewrite


PaECTER is a document-level encoder specifically designed for patents, outperforming existing models in similarity tasks and providing valuable numerical representations for patent documents.
