@inproceedings{zheng-etal-2020-sumsum,
    title = "{SUMSUM}@{FNS}-2020 Shared Task",
    author = "Zheng, Siyan  and
      Lu, Anneliese  and
      Cardie, Claire",
    editor = "El-Haj, Dr Mahmoud  and
      Athanasakou, Dr Vasiliki  and
      Ferradans, Dr Sira  and
      Salzedo, Dr Catherine  and
      Elhag, Dr Ans  and
      Bouamor, Dr Houda  and
      Litvak, Dr Marina  and
      Rayson, Dr Paul  and
      Giannakopoulos, Dr George  and
      Pittaras, Nikiforos",
    booktitle = "Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "COLING",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.fnp-1.25/",
    pages = "148--152",
    abstract = "This paper describes the SUMSUM systems submitted to the Financial Narrative Summarization Shared Task (FNS-2020). We explore a section-based extractive summarization method tailored to the structure of financial reports: our best system parses the report Table of Contents (ToC), splits the report into narrative sections based on the ToC, and applies a BERT-based classifier to each section to determine whether it should be included in the summary. Our best system ranks 4$^{\textrm{th}}$, 1$^{\textrm{st}}$, 2$^{\textrm{nd}}$ and 17$^{\textrm{th}}$ on the Rouge-1, Rouge-2, Rouge-SU4, and Rouge-L official metrics, respectively. We also report results on the validation set using an alternative set of Rouge-based metrics that measure performance with respect to the best-matching of the available gold summaries."
}