@inproceedings{nadeem-ostendorf-2018-estimating,
    title = "Estimating Linguistic Complexity for Science Texts",
    author = "Nadeem, Farah  and
      Ostendorf, Mari",
    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/iwcs-25-ingestion/W18-0505/",
    doi = "10.18653/v1/W18-0505",
    pages = "45--55",
    abstract = "Evaluation of text difficulty is important both for downstream tasks like text simplification, and for supporting educators in classrooms. Existing work on automated text complexity analysis uses linear models with engineered knowledge-driven features as inputs. While this offers interpretability, these models have lower accuracy for shorter texts. Traditional readability metrics have the additional drawback of not generalizing to informational texts such as science. We propose a neural approach, training on science and other informational texts, to mitigate both problems. Our results show that neural methods outperform knowledge-based linear models for short texts, and have the capacity to generalize to genres not present in the training data."
}