Owing to the tremendous size of electronic biomedical documents, users encounter difficulties in seeking useful biomedical information. An efficient and smart access to the relevant biomedical information has become a fundamental need. In this research paper, we set forward a novel biomedical MeSH-based semantic indexing approach to enhance biomedical information retrieval. The proposed semantic indexing approach attempts to strengthen the content representation of both documents and queries by incorporating unambiguous MeSH concepts as well as the adequate senses of ambiguous MeSH concepts. For this purpose, our proposed approach relies on a disambiguation method to identify the adequate senses of ambiguous MeSH concepts and introduces four representation enrichment strategies so as to identify the best appropriate representatives of the adequate sense in the textual entities representation. To prove its effectiveness, the proposed semantic indexing approach was evaluated by intensive experiments. These experiments were carried out on OHSUMED test collection. The results reveal that our proposal outperforms the state-of-the-art approaches and allow us to highlight the most effective strategy.

中文翻译：

---

基于MeSH的语义索引方法可增强生物医学信息检索

由于电子生物医学文档的巨大规模，用户在寻找有用的生物医学信息时遇到了困难。对相关生物医学信息的高效智能访问已成为一项基本需求。在本文中，我们提出了一种新颖的基于MeSH的生物医学语义索引方法，以增强生物医学信息的检索。所提出的语义索引方法试图通过结合明确的MeSH概念以及适当的歧义MeSH概念来增强文档和查询的内容表示。以此目的，我们提出的方法依靠一种歧义消除方法来识别模棱两可的MeSH概念的适当含义，并引入了四种表示形式丰富化策略，以便在文本实体表示中确定适当含义的最佳适当代表。为了证明其有效性，通过大量实验对提出的语义索引方法进行了评估。这些实验是在OHSUMED测试集合上进行的。结果表明，我们的建议优于最新方法，使我们能够强调最有效的策略。