@inproceedings{singh-etal-2020-lt3,
    title = "{LT}3 at {S}em{E}val-2020 Task 8: Multi-Modal Multi-Task Learning for Memotion Analysis",
    author = "Singh, Pranaydeep  and
      Bauwelinck, Nina  and
      Lefever, Els",
    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/jlcl-multiple-ingestion/2020.semeval-1.153/",
    doi = "10.18653/v1/2020.semeval-1.153",
    pages = "1155--1162",
    abstract = "Internet memes have become a very popular mode of expression on social media networks today. Their multi-modal nature, caused by a mixture of text and image, makes them a very challenging research object for automatic analysis. In this paper, we describe our contribution to the SemEval-2020 Memotion Analysis Task. We propose a Multi-Modal Multi-Task learning system, which incorporates {\textquotedblleft}memebeddings{\textquotedblright}, viz. joint text and vision features, to learn and optimize for all three Memotion subtasks simultaneously. The experimental results show that the proposed system constantly outperforms the competition`s baseline, and the system setup with continual learning (where tasks are trained sequentially) obtains the best classification F1-scores."
}