@inproceedings{agarwal-etal-2018-char2char,
    title = "Char2char Generation with Reranking for the {E}2{E} {NLG} Challenge",
    author = "Agarwal, Shubham  and
      Dymetman, Marc  and
      Gaussier, {\'E}ric",
    editor = "Krahmer, Emiel  and
      Gatt, Albert  and
      Goudbeek, Martijn",
    booktitle = "Proceedings of the 11th International Conference on Natural Language Generation",
    month = nov,
    year = "2018",
    address = "Tilburg University, The Netherlands",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W18-6555/",
    doi = "10.18653/v1/W18-6555",
    pages = "451--456",
    abstract = "This paper describes our submission to the E2E NLG Challenge. Recently, neural seq2seq approaches have become mainstream in NLG, often resorting to pre- (respectively post-) processing \textit{delexicalization} (relexicalization) steps at the word-level to handle rare words. By contrast, we train a simple character level seq2seq model, which requires no pre/post-processing (delexicalization, tokenization or even lowercasing), with surprisingly good results. For further improvement, we explore two re-ranking approaches for scoring candidates. We also introduce a synthetic dataset creation procedure, which opens up a new way of creating artificial datasets for Natural Language Generation."
}