Taxonomy Tree Generation from Citation Graph
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917938170167296 |
|---|---|
| author | Hu, Yuntong Li, Zhuofeng Zhang, Zheng Ling, Chen Kanjiani, Raasikh Zhao, Boxin Zhao, Liang |
| author_facet | Hu, Yuntong Li, Zhuofeng Zhang, Zheng Ling, Chen Kanjiani, Raasikh Zhao, Boxin Zhao, Liang |
| contents | Constructing taxonomies from citation graphs is essential for organizing scientific knowledge, facilitating literature reviews, and identifying emerging research trends. However, manual taxonomy construction is labor-intensive, time-consuming, and prone to human biases, often overlooking pivotal but less-cited papers. In this paper, to enable automatic hierarchical taxonomy generation from citation graphs, we propose HiGTL (Hierarchical Graph Taxonomy Learning), a novel end-to-end framework guided by human-provided instructions or preferred topics. Specifically, we propose a hierarchical citation graph clustering method that recursively groups related papers based on both textual content and citation structure, ensuring semantically meaningful and structurally coherent clusters. Additionally, we develop a novel taxonomy node verbalization strategy that iteratively generates central concepts for each cluster, leveraging a pre-trained large language model (LLM) to maintain semantic consistency across hierarchical levels. To further enhance performance, we design a joint optimization framework that fine-tunes both the clustering and concept generation modules, aligning structural accuracy with the quality of generated taxonomies. Extensive experiments demonstrate that HiGTL effectively produces coherent, high-quality taxonomies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03761 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Taxonomy Tree Generation from Citation Graph Hu, Yuntong Li, Zhuofeng Zhang, Zheng Ling, Chen Kanjiani, Raasikh Zhao, Boxin Zhao, Liang Computation and Language Machine Learning Constructing taxonomies from citation graphs is essential for organizing scientific knowledge, facilitating literature reviews, and identifying emerging research trends. However, manual taxonomy construction is labor-intensive, time-consuming, and prone to human biases, often overlooking pivotal but less-cited papers. In this paper, to enable automatic hierarchical taxonomy generation from citation graphs, we propose HiGTL (Hierarchical Graph Taxonomy Learning), a novel end-to-end framework guided by human-provided instructions or preferred topics. Specifically, we propose a hierarchical citation graph clustering method that recursively groups related papers based on both textual content and citation structure, ensuring semantically meaningful and structurally coherent clusters. Additionally, we develop a novel taxonomy node verbalization strategy that iteratively generates central concepts for each cluster, leveraging a pre-trained large language model (LLM) to maintain semantic consistency across hierarchical levels. To further enhance performance, we design a joint optimization framework that fine-tunes both the clustering and concept generation modules, aligning structural accuracy with the quality of generated taxonomies. Extensive experiments demonstrate that HiGTL effectively produces coherent, high-quality taxonomies. |
| title | Taxonomy Tree Generation from Citation Graph |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2410.03761 |