Tag
The paper presents an inductive framework for learning language-independent concept embeddings from cross-linguistic colexification networks combined with textual concept descriptions, enabling embeddings for unseen concepts and correlating well with cross-linguistic similarity measures.
该研究利用RoBERTa掩码语言建模，在科幻与一般小说语料库中对man/woman/person进行掩码替换分析，发现两个语料库都存在跨性别二元的替换，但科幻展现出更强的性别可渗透性与去性别化倾向，为计算文学研究提供了可迁移的分析管线。
This study uses word embeddings to analyze reduplicative constructions in Mandarin Chinese, revealing semantic and pragmatic differentiation and validating distributional semantics for linguistic investigation.
This paper uses word2vec embeddings and neural networks to analyze the inherent fuzziness in parts of speech categorization, creating a 3D semantic space to visualize prototypical words and boundaries between linguistic categories.
This paper introduces Semantic Field Theory (SFT), a computational model for lexical semantics that models meaning through semantic fields, contextual deformation, interaction terms, and energy minimization. It provides formal elements including Gaussian product closure, Möbius inversion for higher-order interactions, and stability conditions.