@inproceedings{shimorina-etal-2019-creating,
    title = "Creating a Corpus for {R}ussian Data-to-Text Generation Using Neural Machine Translation and Post-Editing",
    author = "Shimorina, Anastasia  and
      Khasanova, Elena  and
      Gardent, Claire",
    editor = "Erjavec, Toma{\v{z}}  and
      Marci{\'n}czuk, Micha{\l}  and
      Nakov, Preslav  and
      Piskorski, Jakub  and
      Pivovarova, Lidia  and
      {\v{S}}najder, Jan  and
      Steinberger, Josef  and
      Yangarber, Roman",
    booktitle = "Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W19-3706/",
    doi = "10.18653/v1/W19-3706",
    pages = "44--49",
    abstract = "In this paper, we propose an approach for semi-automatically creating a data-to-text (D2T) corpus for Russian that can be used to learn a D2T natural language generation model. An error analysis of the output of an English-to-Russian neural machine translation system shows that 80{\%} of the automatically translated sentences contain an error and that 53{\%} of all translation errors bear on named entities (NE). We therefore focus on named entities and introduce two post-editing techniques for correcting wrongly translated NEs."
}