CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts
This addresses the problem of integrating new concepts into small taxonomies for applications requiring structured knowledge, representing a strong specific gain.
The paper tackles taxonomy expansion with limited examples by introducing CodeTaxo, which uses code language prompts with large language models, achieving superior performance on five real-world benchmarks and significantly outperforming previous state-of-the-art methods.
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.