@inproceedings{dohare-etal-2018-unsupervised,
    title = "Unsupervised Semantic Abstractive Summarization",
    author = "Dohare, Shibhansh  and
      Gupta, Vivek  and
      Karnick, Harish",
    editor = "Shwartz, Vered  and
      Tabassum, Jeniya  and
      Voigt, Rob  and
      Che, Wanxiang  and
      de Marneffe, Marie-Catherine  and
      Nissim, Malvina",
    booktitle = "Proceedings of {ACL} 2018, Student Research Workshop",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/P18-3011/",
    doi = "10.18653/v1/P18-3011",
    pages = "74--83",
    abstract = "Automatic abstractive summary generation remains a significant open problem for natural language processing. In this work, we develop a novel pipeline for Semantic Abstractive Summarization (SAS). SAS, as introduced by Liu et. al. (2015) first generates an AMR graph of an input story, through which it extracts a summary graph and finally, creates summary sentences from this summary graph. Compared to earlier approaches, we develop a more comprehensive method to generate the story AMR graph using state-of-the-art co-reference resolution and Meta Nodes. Which we then use in a novel unsupervised algorithm based on how humans summarize a piece of text to extract the summary sub-graph. Our algorithm outperforms the state of the art SAS method by 1.7{\%} F1 score in node prediction."
}