SapBERT:
Self-Alignment Pretraining for Biomedical Entity Representations
1. To understand list
- Entity linking
- medical entity linking
- metric
- self-align
2. Abstract
- SapBERT is a pretraining model that self-aligns the representation space of biomedical entites
- Solves problem that accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge.
- Solves problem by design a scalable metric learning framework that can leverage UMLS
- Achieve a new SOTA on six MEL benchmarking datasets.
CoRTEx:
contrastive learning for representing terms via explanations with applications on constructing biomedical knowledge graphs
1. To understand list
- Biomedical Knowledge Graphs
2. Abstract
- CoRTEx is a model using the world knowledge from LLM and propose Contrastive Learning fro Representing Terms via Explanations
- Solves problem that previous contrastive learning models trained with UMLS synonyms struggle at clustering difficult terms and don't generalize well beyond UMLS terms
- Solves problem by using the world knowledge of LLM