Inspicio：面向历史语言的基于大语言模型的开放词汇词义检索
Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages
浏览论文内容
中文总结 AI 辅助
针对历史语言词义消歧需依赖源语言词义清单的问题，提出无需该清单的Inspicio开放词汇检索管道，经多模型评估在感知动词测试集获96% Recall@50，跨域跨语言场景表现具竞争力。
中文摘要 AI 辅助
词义消歧在英语及少数资源丰富的现代语言中已取得快速进展，但该方法仍假设源语言中存在词义清单及词-义映射（Navigli，2026）。这些假设在大多数历史语言和低资源语言中不成立，因为它们的专用词网要么不完整，要么仍在构建中。我们提出Inspicio，一种开放词汇检索管道，无需任何源语言清单或映射，即可将上下文中的词元链接到Open English WordNet（McCrae等人，2020）的同义词集。对于每个出现的词，经指令微调的大语言模型（LLM）生成周围句子的两个英语译文、一小组候选词典式定义及若干候选英语词干。这些输出驱动混合检索步骤，该步骤结合密集定义-同义词集相似度、稀疏词干匹配及最大边际相关性重排序。我们在6×6的大语言模型与句子嵌入模型网格上，对新的双语手动标注拉丁语和古希腊语感知动词集、PREMOVE数据集（Farina，2025）的子集及意大利语的历时样本，评估该管道。最佳配置在感知动词测试集上达到96%的Recall@50，各组件均带来可衡量的增益，且在域外和跨语言设置中仍具竞争力。
英文摘要
Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern languages, but it continues to assume the existence of a sense inventory and a word-to-sense mapping in the source language (Navigli, 2026). These assumptions break down for most historical and low-resource languages, whose dedicated WordNets are either incomplete or still under construction. We present Inspicio, an open-vocabulary retrieval pipeline that links tokens in context to synsets of the Open English WordNet (McCrae et al., 2020) without requiring any source-language inventory or mapping. For each occurrence, an instruction-tuned LLM produces two English translations of the surrounding sentence, a small set of candidate dictionary-style definitions, and a few candidate English lemmas. These outputs drive a hybrid retrieval step that combines dense definition-synset similarity, sparse lemma matching, and Maximal Marginal Relevance re-ranking. We evaluate the pipeline across a 6x6 grid of LLMs and sentence-embedding models on a new bilingual set of manually annotated Latin and Ancient Greek perception verbs, on a subset of PREMOVE dataset (Farina, 2025), and on a diachronic sample of Italian. The best configuration reaches 96% Recall@50 on the perception-verb test set, with each component contributing measurable gains, and remains competitive in the out-of-domain and cross-lingual settings.
发表机构
- University of Foggia（福贾大学）
机构由 AI 辅助整理，请以论文原文为准。
