@inproceedings{jiang-etal-2021-xrjl,
    title = "{XRJL}-{HKUST} at {S}em{E}val-2021 Task 4: {W}ord{N}et-Enhanced Dual Multi-head Co-Attention for Reading Comprehension of Abstract Meaning",
    author = "Jiang, Yuxin  and
      Shou, Ziyi  and
      Wang, Qijun  and
      Wu, Hao  and
      Lin, Fangzhen",
    editor = "Palmer, Alexis  and
      Schneider, Nathan  and
      Schluter, Natalie  and
      Emerson, Guy  and
      Herbelot, Aurelie  and
      Zhu, Xiaodan",
    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://preview.aclanthology.org/jlcl-multiple-ingestion/2021.semeval-1.105/",
    doi = "10.18653/v1/2021.semeval-1.105",
    pages = "793--798",
    abstract = "This paper presents our submitted system to SemEval 2021 Task 4: Reading Comprehension of Abstract Meaning. Our system uses a large pre-trained language model as the encoder and an additional dual multi-head co-attention layer to strengthen the relationship between passages and question-answer pairs, following the current state-of-the-art model DUMA. The main difference is that we stack the passage-question and question-passage attention modules instead of calculating parallelly to simulate re-considering process. We also add a layer normalization module to improve the performance of our model. Furthermore, to incorporate our known knowledge about abstract concepts, we retrieve the definitions of candidate answers from WordNet and feed them to the model as extra inputs. Our system, called WordNet-enhanced DUal Multi-head Co-Attention (WN-DUMA), achieves 86.67{\%} and 89.99{\%} accuracy on the official blind test set of subtask 1 and subtask 2 respectively."
}