用词典辅助跨语言语义投射，自动扩展多语言词汇资源。
Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection
- 基于词典增强的对齐模型，将英文语义概念投射到目标语言。
- 在多个语言上提升精度，相比基线方法效果更优。
- 适合需要低成本构建多语言词汇库的研究者使用。
我们研究通过自动生成词义来将WordNet风格的词汇资源扩展至新语言的任务。方法通过语义投影，将目标语言词元与已有词汇概念关联。给定带词义标注的英文语料及其翻译，本方法将标注的同义词集（synsets）投影到对齐的目标语言词元，并将对应词形（lemmas）分配给这些同义词集。为生成高质量对齐，我们在预训练对齐器基础上引入双语词典，用于增强对齐并过滤错误的词义投射。在多种语言上的评估显示，所提出的“投射-过滤”策略在保持可解释性和资源高效性的同时提升了精度。代码、文档及生成的词义清单已公开于https://github.com/UAlberta-NLP/ExpandNet。
原文摘要 · Abstract (English)
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 https://github.com/UAlberta-NLP/ExpandNet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。