@inproceedings{hua-etal-2022-amrtvsumm,
    title = "{AMRTVS}umm: {AMR}-augmented Hierarchical Network for {TV} Transcript Summarization",
    author = "Hua, Yilun  and
      Deng, Zhaoyuan  and
      Xu, Zhijie",
    editor = "Mckeown, Kathleen",
    booktitle = "Proceedings of the Workshop on Automatic Summarization for Creative Writing",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.creativesumm-1.6/",
    pages = "36--43",
    abstract = "This paper describes our AMRTVSumm system for the SummScreen datasets in the Automatic Summarization for Creative Writing shared task (Creative-Summ 2022). In order to capture the complicated entity interactions and dialogue structures in transcripts of TV series, we introduce a new Abstract Meaning Representation (AMR) (Banarescu et al., 2013), particularly designed to represent individual scenes in an episode. We also propose a new cross-level cross-attention mechanism to incorporate these scene AMRs into a hierarchical encoder-decoder baseline. On both the ForeverDreaming and TVMegaSite datasets of SummScreen, our system consistently outperforms the hierarchical transformer baseline. Compared with the state-of-the-art DialogLM (Zhong et al., 2021), our system still has a lower performance primarily because it is pretrained only on out-of-domain news data, unlike DialogLM, which uses extensive in-domain pretraining on dialogue and TV show data. Overall, our work suggests a promising direction to capture complicated long dialogue structures through graph representations and the need to combine graph representations with powerful pretrained language models."
}