Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction

Tianze Shi and Lillian Lee

In ACL (2021)

Abstract
We propose a transition-based bubble parser to perform coordination structure identification and dependency-based syntactic analysis simultaneously. Bubble representations were proposed in the formal linguistics literature decades ago; they enhance dependency trees by encoding coordination boundaries and internal relationships within coordination structures explicitly. In this paper, we introduce a transition system and neural models for parsing these bubble-enhanced structures. Experimental results on the English Penn Treebank and the English GENIA corpus show that our parsers beat previous state-of-the-art approaches on the task of coordination structure prediction, especially for the subset of sentences with complex coordination structures.

Bibtex

@InProceedings{shi-lee-21-transition,
    title = "Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction"
    author = "Shi, Tianze  and
              Lee, Lillian",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics",
    month = aug,
    year = "2021",
    address = "Online",
    pages = "7167--7182",
    publisher = "Association for Computational Linguistics",
}

Tianze Shi @ Cornell University. Built with jekyll