School of Basic Medical Sciences and the First Affiliated Hospital Department of Radiation Oncology, Zhejiang University School of Medicine, Hangzhou, 310058, China; Zhejiang Provincial Key Laboratory for Microbial Biochemistry and Metabolic Engineering, Hangzhou, 310058, China.
School of Electronics and Information Engineering, Taizhou University, Taizhou, 318000, China.
Comput Biol Med. 2023 Nov;166:107475. doi: 10.1016/j.compbiomed.2023.107475. Epub 2023 Sep 9.
Precise semantic representation is important for allowing machines to truly comprehend the meaning of natural language text, especially biomedical literature. Although the semantic relations among words in a single sentence may be accurately represented with existing approaches, relations between two sentences cannot yet be accurately modeled, which leads to a lack of contextual information and difficulty in performing interpretable semantic inference. Additionally, it is challenging to merge semantic representations curated by different experts. These critical challenges are insufficiently addressed by existing methods. In this paper, we present a framework for structured semantic representation (FSSR) to address these issues. FSSR uses a double-layer structure Construct that combines Paradigm and Instance to represent the semantics of a word or a sentence. It uses six types of rules to represent the semantic relations between sentence Constructs and uses a Computational Model to represent an action. FSSR is a graph-based representation of semantics, in which a node represents a Construct or a Paradigm. Two nodes are connected by an edge (a rule). In addition, FSSR enables interpretable inference and active acquisition of new information, as illustrated in a case study. This case study models the semantics of a cancer prognostic analysis article and reproduces its text results and charts. We provide a website that visualizes the inference process (http://cragraph.synergylab.cn).
精确的语义表示对于使机器真正理解自然语言文本的含义非常重要，特别是在生物医学文献中。虽然现有方法可以准确地表示单句中单词之间的语义关系，但无法准确地建模两个句子之间的关系，这导致缺乏上下文信息，难以进行可解释的语义推理。此外，合并由不同专家精心制作的语义表示也具有挑战性。这些关键挑战在现有方法中没有得到充分解决。在本文中，我们提出了一种结构化语义表示框架 (FSSR) 来解决这些问题。FSSR 使用双层结构 Construct 来结合范例和实例来表示单词或句子的语义。它使用六种类型的规则来表示句子 Construct 之间的语义关系，并使用计算模型来表示一个动作。FSSR 是一种基于图的语义表示，其中节点表示一个 Construct 或范例。两个节点由边（规则）连接。此外，FSSR 还支持可解释的推理和新信息的主动获取，如案例研究所示。该案例研究对癌症预后分析文章的语义进行建模，并再现其文本结果和图表。我们提供了一个可视化推理过程的网站（http://cragraph.synergylab.cn）。
