Semantic Dependency Parsing with Edge GNNs

Songlin Yang; Kewei Tu

EMNLP 2022finding2 citations

Semantic Dependency Parsing with Edge GNNs

Abstract

Second-order neural parsers have obtained high accuracy in semantic dependency parsing. Inspired by the factor graph representation of second-order parsing, we propose edge graph neural networks (E-GNNs). In an E-GNN, each node corresponds to a dependency edge, and the neighbors are defined in terms of sibling, co-parent, and grandparent relationships. We conduct experiments on SemEval 2015 Task 18 English datasets, showing the superior performance of E-GNNs.

BibTeX

@inproceedings{yang-tu-2022-semantic,
    title = "Semantic Dependency Parsing with Edge {GNN}s",
    author = "Yang, Songlin  and
      Tu, Kewei",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-emnlp.452/",
    doi = "10.18653/v1/2022.findings-emnlp.452",
    pages = "6096--6102"
}