Neighborhood-Aware Dual Biomedical Entity Linking

• URL: http://arxiv.org/abs/2608.04144v1
• Date: Tue, 04 Aug 2026 18:55:14 GMT
• Title: Neighborhood-Aware Dual Biomedical Entity Linking
• Abstract summary: PILOT is a three-stage framework made up of neighborhood-aware retrieval, dual reranking, and score fusion.<n> PILOT achieves the state of the art on average across five widely-used benchmarks and remains efficient at inference.
• Score: 4.745611914403518
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Hybrid-IR: Dual-Path Hybrid Retrieval with Iterative Reasoning for Complex Medical Question Answering [19.561452074492653]
  We present a dual-path retrieval framework with an iterative retrieval-reasoning mechanism termed "Hybrid-IR"<n>The proposed Hybrid-IR integrates graph-based retrieval for exploration of structured knowledge and dense retrieval for fine-grained semantic matching.<n> Experiments on three widely used medical QA benchmarks demonstrate the effectiveness of our Hybrid-IR.
  arXiv  Detail & Related papers  (2026-06-24T03:09:50Z)
• Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework [60.82334952881798]
  Protein-Text Question Answering (QA) is crucial for interpreting biological sequences through natural language.<n>We propose 2D-ProteinRAG, a novel framework that empowers Large Language Models (LLMs) to operate within the gold-standard biological research workflow.<n>We show that 2D-Protein consistently achieves state-of-the-art performance, outperforming fine-tuned baselines and other RAG methods.
  arXiv  Detail & Related papers  (2026-05-17T05:03:24Z)
• A Unified Biomedical Named Entity Recognition Framework with Large Language Models [44.92744341698289]
  We propose a unified Biomedical Named Entity Recognition (BioNER) framework based on Large Language Models (LLMs)<n>We first reformulate BioNER as a text generation task and design a symbolic tagging strategy to jointly handle both flat and nested entities.<n>We perform bilingual joint fine-tuning across multiple Chinese and English datasets.
  arXiv  Detail & Related papers  (2025-10-10T01:33:54Z)
• Biomedical Entity Linking as Multiple Choice Question Answering [48.74212158495695]
  We present BioELQA, a novel model that treats Biomedical Entity Linking as Multiple Choice Question Answering. We first obtains candidate entities with a fast retriever, jointly presents the mention and candidate entities to a generator, and then outputs the predicted symbol associated with its chosen entity. To improve generalization for long-tailed entities, we retrieve similar labeled training instances as clues and the input with retrieved instances for the generator.
  arXiv  Detail & Related papers  (2024-02-23T08:40:38Z)
• Benchingmaking Large Langage Models in Biomedical Triple Extraction [13.022101126299269]
  This work mainly focuses on sentence-level biomedical triple extraction. The absence of a high-quality biomedical triple extraction dataset impedes the progress in developing robust triple extraction systems. We present GIT, an expert-annotated biomedical triple extraction dataset.
  arXiv  Detail & Related papers  (2023-10-27T20:15:23Z)
• Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization [9.422435686239538]
  Biomedical entity linking and event extraction are two crucial tasks to support text understanding and retrieval in the biomedical domain. Previous research typically solves these two tasks separately or in a pipeline, leading to error propagation. We propose joint biomedical entity linking and event extraction by regarding the event structures and entity references in knowledge bases as latent variables.
  arXiv  Detail & Related papers  (2023-05-24T02:30:31Z)
• EBOCA: Evidences for BiOmedical Concepts Association Ontology [55.41644538483948]
  This paper proposes EBOCA, an ontology that describes (i) biomedical domain concepts and associations between them, and (ii) evidences supporting these associations. Test data coming from a subset of DISNET and automatic association extractions from texts has been transformed to create a Knowledge Graph that can be used in real scenarios.
  arXiv  Detail & Related papers  (2022-08-01T18:47:03Z)
• Discovering Drug-Target Interaction Knowledge from Biomedical Literature [107.98712673387031]
  The Interaction between Drugs and Targets (DTI) in human body plays a crucial role in biomedical science and applications. As millions of papers come out every year in the biomedical domain, automatically discovering DTI knowledge from literature becomes an urgent demand in the industry. We explore the first end-to-end solution for this task by using generative approaches. We regard the DTI triplets as a sequence and use a Transformer-based model to directly generate them without using the detailed annotations of entities and relations.
  arXiv  Detail & Related papers  (2021-09-27T17:00:14Z)
• Self-supervised Answer Retrieval on Clinical Notes [68.87777592015402]
  We introduce CAPR, a rule-based self-supervision objective for training Transformer language models for domain-specific passage matching. We apply our objective in four Transformer-based architectures: Contextual Document Vectors, Bi-, Poly- and Cross-encoders. We report that CAPR outperforms strong baselines in the retrieval of domain-specific passages and effectively generalizes across rule-based and human-labeled passages.
  arXiv  Detail & Related papers  (2021-08-02T10:42:52Z)
• Fast and Effective Biomedical Entity Linking Using a Dual Encoder [48.86736921025866]
  We propose a BERT-based dual encoder model that resolves multiple mentions in a document in one shot. We show that our proposed model is multiple times faster than existing BERT-based models while being competitive in accuracy for biomedical entity linking.
  arXiv  Detail & Related papers  (2021-03-08T19:32:28Z)
• Clustering-based Inference for Biomedical Entity Linking [40.78384867437563]
  We introduce a model in which linking decisions can be made not merely by linking to a knowledge base entity but also by grouping multiple mentions together via clustering and jointly making linking predictions. In experiments on the largest publicly available biomedical dataset, we improve the best independent prediction for entity linking by 3.0 points of accuracy.
  arXiv  Detail & Related papers  (2020-10-21T19:16:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.