arXiv cs.AI· David Basil, Chirooth Girigowda, Bradley Hauer, Sahir Momin, Ning Shi, Grzegorz Kondrak·· 4 小时前AI 评分25
基于词典跨语言词义投影自动生成概念词汇化
Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection
AI 导读
一项 arXiv 研究提出通过词义生成自动将 WordNet 式词汇资源扩展到新语言的方法:在词义标注的英文语料及其翻译上,把英文同义词集投影到对齐的目标语言 token 并指派对应词元。方法用双语词典增强预训练对齐器并过滤错误投影,在多语言上与词典基线和大语言模型基线对比,结果显示该投影加过滤策略提升了精确度,同时保持可解释性与资源高效性,代码和生成的词义清单已开源。
正文 · 原文
Abstract:We study the task of automatically expanding WordNet-style lexical resources to new languages through sense generation. We generate senses by associating target-language lemmas with existing lexical concepts via semantic projection. Given a sense-tagged English corpus and its translation, our method projects the annotated synsets onto aligned target-language tokens and assigns the corresponding lemmas to those synsets. To generate alignments and ensure their quality, we augment a pretrained base aligner with a bilingual dictionary, which is also used to filter incorrect sense projections. We evaluate the method on multiple languages, comparing it to prior methods, as well as dictionary-based and large language model baselines. Results show that the proposed project-and-filter strategy improves precision while remaining interpretable and resource- efficient. We release our code, documentation, and generated sense inventories at this https URL.
| Comments: | Paper presented at Canadian AI 2026 |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2604.14397 [cs.CL] |
| (or arXiv:2604.14397v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2604.14397 arXiv-issued DOI via DataCite |
Submission history
From: Ning Shi [view email]
[v1]
Wed, 15 Apr 2026 20:27:26 UTC (290 KB)
[v2]
Mon, 8 Jun 2026 21:41:00 UTC (88 KB)
[v3]
Fri, 13 Nov 2026 18:49:40 UTC (333 KB)
来源:arXiv cs.AI · arxiv.org