2024/08/17 by Qingkai Zeng, Zeng, Qingkai, Yuyang Bai +9 · 5 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Semantic Web and Ontologies #Software Engineering Research
paper · pdf · doi:10.48550/arxiv.2408.09070
openalex publication_date 2024/08/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Taxonomies play a crucial role in various applications by providing a structural representation of knowledge. The task of taxonomy expansion involves integrating emerging concepts into existing taxonomies by identifying appropriate parent concepts for these new query concepts. Previous approaches typically relied on self-supervised methods that generate annotation data from existing taxonomies. However, these methods are less effective when the existing taxonomy is small (fewer than 100 entities). In this work, we introduce CodeTaxo, a novel approach that leverages large language models through code language prompts to capture the taxonomic structure. Extensive experiments on five real-world benchmarks from different domains demonstrate that CodeTaxo consistently achieves superior performance across all evaluation metrics, significantly outperforming previous state-of-the-art methods. The code and data are available at https://github.com/QingkaiZeng/CodeTaxo-Pub.