@inproceedings{glocker-markianos-wright-2020-textmarkers,
    title = {{T}{\"e}{X}tmarkers at {S}em{E}val-2020 Task 10: Emphasis Selection with Agreement Dependent Crowd Layers},
    author = "Glocker, Kevin  and
      Markianos Wright, Stefanos Andreas",
    editor = "Herbelot, Aurelie  and
      Zhu, Xiaodan  and
      Palmer, Alexis  and
      Schneider, Nathan  and
      May, Jonathan  and
      Shutova, Ekaterina",
    booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
    month = dec,
    year = "2020",
    address = "Barcelona (online)",
    publisher = "International Committee for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.semeval-1.222/",
    doi = "10.18653/v1/2020.semeval-1.222",
    pages = "1698--1703",
    abstract = "In visual communication, the ability of a short piece of text to catch someone{'}s eye in a single glance or from a distance is of paramount importance. In our approach to the SemEval-2020 task ``Emphasis Selection For Written Text in Visual Media'', we use contextualized word representations from a pretrained model of the state-of-the-art BERT architecture together with a stacked bidirectional GRU network to predict token-level emphasis probabilities. For tackling low inter-annotator agreement in the dataset, we attempt to model multiple annotators jointly by introducing initialization with agreement dependent noise to a crowd layer architecture. We found our approach to both perform substantially better than initialization with identities for this purpose and to outperform a baseline trained with token level majority voting. Our submission system reaches substantially higher Match m on the development set than the task baseline (0.779), but only slightly outperforms the test set baseline (0.754) using a three model ensemble."
}