ACL 2022long8 citations

Unsupervised Dependency Graph Network

Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li, Jie Zhou, Aaron Courville

Abstract

Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, some self-attention heads correspond well to individual dependency types. Inspired by these developments, we propose a new competitive mechanism that encourages these attention heads to model different dependency relations. We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task. Experiment results show that UDGN achieves very strong unsupervised dependency parsing performance without gold POS tags and any other external information. The competitive gated heads show a strong correlation with human-annotated dependency types. Furthermore, the UDGN can also achieve competitive performance on masked language modeling and sentence textual similarity tasks.

BibTeX
@inproceedings{shen-etal-2022-unsupervised,
    title = "Unsupervised Dependency Graph Network",
    author = "Shen, Yikang  and
      Tan, Shawn  and
      Sordoni, Alessandro  and
      Li, Peng  and
      Zhou, Jie  and
      Courville, Aaron",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.327/",
    doi = "10.18653/v1/2022.acl-long.327",
    pages = "4767--4784"
}
Unsupervised Dependency Graph Network · ACL 2022