Search papers, labs, and topics across Lattice.
This paper introduces PILOT, a novel three-stage framework for biomedical entity linking that enhances the grounding of mentions in clinical and scientific texts to a structured knowledge base. By leveraging neighborhood-aware retrieval and dual reranking, PILOT effectively addresses the challenges of entity ambiguity and corpus-specific annotation conventions, achieving state-of-the-art performance across five benchmarks. The method's efficiency at inference makes it a practical solution for applications in literature-scale information extraction and patient-record normalization.
PILOT redefines biomedical entity linking by achieving state-of-the-art results while maintaining efficiency, overcoming the complexities of ambiguous mentions and diverse annotation standards.
Biomedical entity linking grounds mentions in clinical and scientific text to entities in a curated knowledge base (KB) with ontological structure, which supports downstream applications such as literature-scale information extraction and patient-record normalization. The task has several challenges at once: the KB contains large numbers of entities, mentions are often ambiguous, and gold labels follow annotation conventions specific to each corpus. To address these challenges, we propose PILOT, a three-stage framework made up of neighborhood-aware retrieval, dual reranking, and score fusion. The retriever injects ontological structure from both the query and KB side, by reformulating mentions and pooling entity embeddings. The retrieved pool is then scored from two complementary views, one over surface forms and one over context, and fused together. PILOT achieves the state of the art on average across five widely-used benchmarks and remains efficient at inference.
