Construction of Hyper-Relational Knowledge Graphs Using Pre-Trained Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913269917155328 |
|---|---|
| author | Datta, Preetha Vitiugin, Fedor Chizhikova, Anastasiia Sawhney, Nitin |
| author_facet | Datta, Preetha Vitiugin, Fedor Chizhikova, Anastasiia Sawhney, Nitin |
| contents | Extracting hyper-relations is crucial for constructing comprehensive knowledge graphs, but there are limited supervised methods available for this task. To address this gap, we introduce a zero-shot prompt-based method using OpenAI's GPT-3.5 model for extracting hyper-relational knowledge from text. Comparing our model with a baseline, we achieved promising results, with a recall of 0.77. Although our precision is currently lower, a detailed analysis of the model outputs has uncovered potential pathways for future research in this area. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11786 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Construction of Hyper-Relational Knowledge Graphs Using Pre-Trained Large Language Models Datta, Preetha Vitiugin, Fedor Chizhikova, Anastasiia Sawhney, Nitin Computation and Language Artificial Intelligence Extracting hyper-relations is crucial for constructing comprehensive knowledge graphs, but there are limited supervised methods available for this task. To address this gap, we introduce a zero-shot prompt-based method using OpenAI's GPT-3.5 model for extracting hyper-relational knowledge from text. Comparing our model with a baseline, we achieved promising results, with a recall of 0.77. Although our precision is currently lower, a detailed analysis of the model outputs has uncovered potential pathways for future research in this area. |
| title | Construction of Hyper-Relational Knowledge Graphs Using Pre-Trained Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.11786 |