@inproceedings{gao-etal-2023-greedycas,
    title = "{G}reedy{CAS}: Unsupervised Scientific Abstract Segmentation with Normalized Mutual Information",
    author = "Gao, Yingqiang  and
      Lam, Jessica  and
      Gu, Nianlong  and
      Hahnloser, Richard",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.emnlp-main.372/",
    doi = "10.18653/v1/2023.emnlp-main.372",
    pages = "6093--6108",
    abstract = "The abstracts of scientific papers typically contain both premises (e.g., background and observations) and conclusions. Although conclusion sentences are highlighted in structured abstracts, in non-structured abstracts the concluding information is not explicitly marked, which makes the automatic segmentation of conclusions from scientific abstracts a challenging task. In this work, we explore Normalized Mutual Information (NMI) as a means for abstract segmentation. We consider each abstract as a recurrent cycle of sentences and place two segmentation boundaries by greedily optimizing the NMI score between the two segments, assuming that conclusions are strongly semantically linked with preceding premises. On non-structured abstracts, our proposed unsupervised approach GreedyCAS achieves the best performance across all evaluation metrics; on structured abstracts, GreedyCAS outperforms all baseline methods measured by $P_k$. The strong correlation of NMI to our evaluation metrics reveals the effectiveness of NMI for abstract segmentation."
}