@inproceedings{koto-etal-2020-indolem,
    title = "{I}ndo{LEM} and {I}ndo{BERT}: A Benchmark Dataset and Pre-trained Language Model for {I}ndonesian {NLP}",
    author = "Koto, Fajri  and
      Rahimi, Afshin  and
      Lau, Jey Han  and
      Baldwin, Timothy",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.coling-main.66/",
    doi = "10.18653/v1/2020.coling-main.66",
    pages = "757--770",
    abstract = "Although the Indonesian language is spoken by almost 200 million people and the 10th most spoken language in the world, it is under-represented in NLP research. Previous work on Indonesian has been hampered by a lack of annotated datasets, a sparsity of language resources, and a lack of resource standardization. In this work, we release the IndoLEM dataset comprising seven tasks for the Indonesian language, spanning morpho-syntax, semantics, and discourse. We additionally release IndoBERT, a new pre-trained language model for Indonesian, and evaluate it over IndoLEM, in addition to benchmarking it against existing resources. Our experiments show that IndoBERT achieves state-of-the-art performance over most of the tasks in IndoLEM."
}