@inproceedings{el-khettari-etal-2025-summarization,
    title = "Summarization for Generative Relation Extraction in the Microbiome Domain",
    author = "El Khettari, Oumaima  and
      Quiniou, Solen  and
      Chaffron, Samuel",
    editor = "Bechet, Fr{\'e}d{\'e}ric  and
      Chifu, Adrian-Gabriel  and
      Pinel-sauvagnat, Karen  and
      Favre, Benoit  and
      Maes, Eliot  and
      Nurbakova, Diana",
    booktitle = "Actes de l'atelier Traitement du langage m{\'e}dical {\`a} l'{\'e}poque des LLMs 2025 (MLP-LLM)",
    month = "6",
    year = "2025",
    address = "Marseille, France",
    publisher = "ATALA {\textbackslash}{\textbackslash}{\&} ARIA",
    url = "https://preview.aclanthology.org/corrections-2025-10/2025.jeptalnrecital-mlpllm.6/",
    pages = "68--82",
    abstract = "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."
}