Grouping Synonyms by Definitions

关键点分析需要结构恢复：任务定义、数据集诊断及结构感知基准

Key Point Analysis Needs Structure Recovery: Task Definition, Dataset Diagnosis, and a Structure-Aware Benchmark

该研究定义关键点分析（KPA）为结构化预测问题，诊断现有KPA基准缺陷，构建人机协同标注的结构感知基准并发布相关资源，为KPA研究提供支持

通过双通道文本提示和图像增强的CLIP实现视觉词义消歧

Visual Word Sense Disambiguation with CLIP through Dual-Channel Text Prompting and Image Augmentations

本文提出通过CLIP和双通道提示与图像增强实现视觉词义消歧，提升MRR和命中率，验证了精确提示的有效性。

Sõnajaht：用于反向词典构建的定义嵌入与语义搜索

Sõnajaht: Definition Embeddings and Semantic Search for Reverse Dictionary Creation

本文提出基于预训练语言模型与近似最近邻搜索的反向词典系统，应用于爱沙尼亚语词典 Sõnaveeb，无需训练即可在单语和跨语言设置中取得优异的中位排名。

Extraction of semantic relations from a Basque monolingual dictionary using Constraint Grammar

This paper deals with the exploitation of dictionaries for the semi-automatic construction of lexicons and lexical knowledge bases. The final goal of our research is to enrich the Basque Lexical Database with semantic information such as senses, definitions, semantic relations, etc., extracted from a Basque monolingual dictionary. The work here presented focuses on the extraction of the semantic relations that best characterise the headword, that is, those of synonymy, antonymy, hypernymy, and other relations marked by specific relators and derivation. All nominal, verbal and adjectival entrie…

说得出，却不知道：激进GGUF量化的小语言模型仍能写出它们已无法定义的罕见词

Saying, Not Knowing: Aggressively GGUF-Quantized Small Language Models Still Write Rare Words They Can No Longer Define

本研究审计27个GGUF量化小语言模型，发现激进量化至Q2级别时，子2B模型罕见词定义能力大幅下降，而生成流畅性保留，需按产物逐一验证。