@inproceedings{vajjala-lucic-2018-onestopenglish,
    title = "{O}ne{S}top{E}nglish corpus: A new corpus for automatic readability assessment and text simplification",
    author = "Vajjala, Sowmya  and
      Lu{\v{c}}i{\'c}, Ivana",
    editor = "Tetreault, Joel  and
      Burstein, Jill  and
      Kochmar, Ekaterina  and
      Leacock, Claudia  and
      Yannakoudakis, Helen",
    booktitle = "Proceedings of the Thirteenth Workshop on Innovative Use of {NLP} for Building Educational Applications",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W18-0535/",
    doi = "10.18653/v1/W18-0535",
    pages = "297--304",
    abstract = "This paper describes the collection and compilation of the OneStopEnglish corpus of texts written at three reading levels, and demonstrates its usefulness for through two applications - automatic readability assessment and automatic text simplification. The corpus consists of 189 texts, each in three versions (567 in total). The corpus is now freely available under a CC by-SA 4.0 license and we hope that it would foster further research on the topics of readability assessment and text simplification."
}