@inproceedings{rezapour-etal-2024-two,
    title = "Two-Stage Graph-Augmented Summarization of Scientific Documents",
    author = "Rezapour, Rezvaneh  and
      Ge, Yubin  and
      Han, Kanyao  and
      Jeong, Ray  and
      Diesner, Jana",
    editor = "Peled-Cohen, Lotem  and
      Calderon, Nitay  and
      Lissak, Shir  and
      Reichart, Roi",
    booktitle = "Proceedings of the 1st Workshop on NLP for Science (NLP4Science)",
    month = nov,
    year = "2024",
    address = "Miami, FL, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2024.nlp4science-1.5/",
    doi = "10.18653/v1/2024.nlp4science-1.5",
    pages = "36--46",
    abstract = "Automatic text summarization helps to digest the vast and ever-growing amount of scientific publications. While transformer-based solutions like BERT and SciBERT have advanced scientific summarization, lengthy documents pose a challenge due to the token limits of these models. To address this issue, we introduce and evaluate a two-stage model that combines an extract-then-compress framework. Our model incorporates a {\textquotedblleft}graph-augmented extraction module{\textquotedblright} to select order-based salient sentences and an {\textquotedblleft}abstractive compression module{\textquotedblright} to generate concise summaries. Additionally, we introduce the *BioConSumm* dataset, which focuses on biodiversity conservation, to support underrepresented domains and explore domain-specific summarization strategies. Out of the tested models, our model achieves the highest ROUGE-2 and ROUGE-L scores on our newly created dataset (*BioConSumm*) and on the *SUMPUBMED* dataset, which serves as a benchmark in the field of biomedicine."
}