In this paper we argue in favor of the radial semantic structure of polysemous entries from the New Oxford Dictionary of English (NODE) and the Merriam-Webster dictionary. We formalized four polysemy theories as algorithms linking word senses into polysemy networks, considering the semantic similarity of dictionary definitions calculated using large language models. Chaining algorithms maximized similarity within polysemy nets and adequately distinguished senses that in the two dictionaries are directly related from those more distant.

中文翻译：

---

两本英语词典中的一词多义模型

在本文中，我们赞成新牛津英语词典（NODE）和韦氏词典中多义词条的径向语义结构。考虑到使用大型语言模型计算的词典定义的语义相似性，我们将四种多义理论形式化为将词义链接到多义网络的算法。链接算法最大限度地提高了多义网络内的相似性，并充分区分了两个词典中直接相关的含义和较远的含义。