@inproceedings{debenedetto-2024-linearization,
    title = "Linearization Order Matters for {AMR}-to-Text Generation Input",
    author = "DeBenedetto, Justin",
    editor = "Xue, Nianwen  and
      Martin, James",
    booktitle = "Proceedings of the 2024 UMR Parsing Workshop",
    month = jun,
    year = "2024",
    address = "Boulder, Colorado",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.umrpw-1.1/",
    pages = "1--7",
    abstract = "Abstract Meaning Representation (AMR) is a semantic graph formalism designed to capture sentence meaning using a directed graph. Many systems treat AMR-to-text generation as a sequence-to-sequence problem, drawing upon existing models. The largest AMR dataset (AMR 3.0) provides a sequence format which is considered equivalent to the graph format. However, due to the position-sensitive nature of sequence-to-sequence models, graph traversal order affects system performance. In this work we explore the effect that different, valid orderings have on the performance of sequence-to-sequence AMR-to-text systems and find that changing the traversal order can result in a BLEU score drop of up to 17.5 on a state-of-the-art system."
}