CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908379468791808 |
|---|---|
| author | Zeng, Qingkai Bai, Yuyang Tan, Zhaoxuan Wu, Zhenyu Feng, Shangbin Jiang, Meng |
| author_facet | Zeng, Qingkai Bai, Yuyang Tan, Zhaoxuan Wu, Zhenyu Feng, Shangbin Jiang, Meng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09070 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts Zeng, Qingkai Bai, Yuyang Tan, Zhaoxuan Wu, Zhenyu Feng, Shangbin Jiang, Meng Computation and Language Information Retrieval 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. |
| title | CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2408.09070 |