@inproceedings{faille-etal-2020-natural,
    title = "The Natural Language Pipeline, Neural Text Generation and Explainability",
    author = "Faille, Juliette  and
      Gatt, Albert  and
      Gardent, Claire",
    editor = "Alonso, Jose M.  and
      Catala, Alejandro",
    booktitle = "2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence",
    month = nov,
    year = "2020",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.nl4xai-1.5/",
    pages = "16--21",
    abstract = "End-to-end encoder-decoder approaches to data-to-text generation are often black boxes whose predictions are difficult to explain. Breaking up the end-to-end model into sub-modules is a natural way to address this problem. The traditional pre-neural Natural Language Generation (NLG) pipeline provides a framework for breaking up the end-to-end encoder-decoder. We survey recent papers that integrate traditional NLG submodules in neural approaches and analyse their explainability. Our survey is a first step towards building explainable neural NLG models."
}