将生物医学实体链接视为多项选择题问答
Biomedical Entity Linking as Multiple Choice Question Answering
AI总结：
针对生物医学实体链接中细粒度与长尾实体的挑战，提出将该任务转化为多项选择题问答的BioELQA模型，通过显式比较候选实体、拼接相似标注实例提升泛化，在多数据集上超越现有最优基线。
摘要：
尽管生物医学实体链接（BioEL）借助预训练语言模型已取得显著进展，但在细粒度和长尾实体方面仍存在挑战。为应对这些挑战，我们提出BioELQA——一种将生物医学实体链接视为多项选择题问答的新型模型。BioELQA首先通过快速检索器获取候选实体，将提及与候选实体共同输入生成器，随后输出与所选实体关联的预测符号。这种表述方式可实现不同候选实体的显式比较，从而捕捉提及与实体之间以及实体自身之间的细粒度交互。为提升对长尾实体的泛化能力，我们检索相似的带标注训练实例作为线索，并将检索到的实例与输入拼接后送入生成器。大量实验结果表明，BioELQA在多个数据集上的表现优于现有最优基线模型。
英文摘要：
Although biomedical entity linking (BioEL) has made significant progress with pre-trained language models, challenges still exist for fine-grained and long-tailed entities. To address these challenges, we present BioELQA, a novel model that treats Biomedical Entity Linking as Multiple Choice Question Answering. BioELQA 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. This formulation enables explicit comparison of different candidate entities, thus capturing fine-grained interactions between mentions and entities, as well as among entities themselves. To improve generalization for long-tailed entities, we retrieve similar labeled training instances as clues and concatenate the input with retrieved instances for the generator. Extensive experimental results show that BioELQA outperforms state-of-the-art baselines on several datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
