@inproceedings{de-hertog-tack-2018-deep,
    title = "Deep Learning Architecture for Complex Word Identification",
    author = {De Hertog, Dirk  and
      Tack, Ana{\"i}s},
    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/jlcl-multiple-ingestion/W18-0539/",
    doi = "10.18653/v1/W18-0539",
    pages = "328--334",
    abstract = "We describe a system for the CWI-task that includes information on 5 aspects of the (complex) lexical item, namely distributional information of the item itself, morphological structure, psychological measures, corpus-counts and topical information. We constructed a deep learning architecture that combines those features and apply it to the probabilistic and binary classification task for all English sets and Spanish. We achieved reasonable performance on all sets with best performances seen on the probabilistic task, particularly on the English news set (MAE 0.054 and F1-score of 0.872). An analysis of the results shows that reasonable performance can be achieved with a single architecture without any domain-specific tweaking of the parameter settings and that distributional features capture almost all of the information also found in hand-crafted features."
}