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.
@article{arxiv.2506.08647,
title = {Summarization for Generative Relation Extraction in the Microbiome Domain},
author = {Oumaima El Khettari and Solen Quiniou and Samuel Chaffron},
journal= {arXiv preprint arXiv:2506.08647},
year = {2025}
}