@inproceedings{taya-etal-2021-ochadai,
    title = "{OCHADAI}-{KYOTO} at {S}em{E}val-2021 Task 1: Enhancing Model Generalization and Robustness for Lexical Complexity Prediction",
    author = "Taya, Yuki  and
      Kanashiro Pereira, Lis  and
      Cheng, Fei  and
      Kobayashi, Ichiro",
    booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.semeval-1.2",
    doi = "10.18653/v1/2021.semeval-1.2",
    pages = "17--23",
    abstract = "We propose an ensemble model for predicting the lexical complexity of words and multiword expressions (MWEs). The model receives as input a sentence with a target word or MWE and outputs its complexity score. Given that a key challenge with this task is the limited size of annotated data, our model relies on pretrained contextual representations from different state-of-the-art transformer-based language models (i.e., BERT and RoBERTa), and on a variety of training methods for further enhancing model generalization and robustness: multi-step fine-tuning and multi-task learning, and adversarial training. Additionally, we propose to enrich contextual representations by adding hand-crafted features during training. Our model achieved competitive results and ranked among the top-10 systems in both sub-tasks.",
}