@inproceedings{same-van-deemter-2020-linguistic,
    title = "A Linguistic Perspective on Reference: Choosing a Feature Set for Generating Referring Expressions in Context",
    author = "Same, Fahime  and
      van Deemter, Kees",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.coling-main.403/",
    doi = "10.18653/v1/2020.coling-main.403",
    pages = "4575--4586",
    abstract = "This paper reports on a structured evaluation of feature-based Machine Learning algorithms for selecting the form of a referring expression in discourse context. Based on this evaluation, we selected seven feature sets from the literature, amounting to 65 distinct linguistic features. The features were then grouped into 9 broad classes. After building Random Forest models, we used Feature Importance Ranking and Sequential Forward Search methods to assess the {\textquotedblleft}importance{\textquotedblright} of the features. Combining the results of the two methods, we propose a consensus feature set. The 6 features in our consensus set come from 4 different classes, namely grammatical role, inherent features of the referent, antecedent form and recency."
}