Summarization for Generative Relation Extraction in the Microbiome Domain
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910998786473984 |
|---|---|
| author | Khettari, Oumaima El Quiniou, Solen Chaffron, Samuel |
| author_facet | Khettari, Oumaima El Quiniou, Solen Chaffron, Samuel |
| contents | We explore a generative relation extraction (RE) pipeline tailored to the study of interactions in the intestinal microbiome, a complex and low-resource biomedical domain. Our method leverages summarization with large language models (LLMs) to refine context before extracting relations via instruction-tuned generation. Preliminary results on a dedicated corpus show that summarization improves generative RE performance by reducing noise and guiding the model. However, BERT-based RE approaches still outperform generative models. This ongoing work demonstrates the potential of generative methods to support the study of specialized domains in low-resources setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08647 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Summarization for Generative Relation Extraction in the Microbiome Domain Khettari, Oumaima El Quiniou, Solen Chaffron, Samuel Computation and Language Artificial Intelligence We explore a generative relation extraction (RE) pipeline tailored to the study of interactions in the intestinal microbiome, a complex and low-resource biomedical domain. Our method leverages summarization with large language models (LLMs) to refine context before extracting relations via instruction-tuned generation. Preliminary results on a dedicated corpus show that summarization improves generative RE performance by reducing noise and guiding the model. However, BERT-based RE approaches still outperform generative models. This ongoing work demonstrates the potential of generative methods to support the study of specialized domains in low-resources setting. |
| title | Summarization for Generative Relation Extraction in the Microbiome Domain |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.08647 |