@inproceedings{koto-etal-2020-liputan6,
    title = "Liputan6: A Large-scale {I}ndonesian Dataset for Text Summarization",
    author = "Koto, Fajri  and
      Lau, Jey Han  and
      Baldwin, Timothy",
    editor = "Wong, Kam-Fai  and
      Knight, Kevin  and
      Wu, Hua",
    booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
    month = dec,
    year = "2020",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.aacl-main.60/",
    doi = "10.18653/v1/2020.aacl-main.60",
    pages = "598--608",
    abstract = "In this paper, we introduce a large-scale Indonesian summarization dataset. We harvest articles from Liputan6.com, an online news portal, and obtain 215,827 document{--}summary pairs. We leverage pre-trained language models to develop benchmark extractive and abstractive summarization methods over the dataset with multilingual and monolingual BERT-based models. We include a thorough error analysis by examining machine-generated summaries that have low ROUGE scores, and expose both issues with ROUGE itself, as well as with extractive and abstractive summarization models."
}