Tianze Shi Home Publications

Semantic Role Labeling as Syntactic Dependency Parsing

Tianze Shi, Igor Malioutov, and Ozan İrsoy

In EMNLP (2020)

Abstract
We reduce the task of (span-based) PropBank-style semantic role labeling (SRL) to syntactic dependency parsing. Our approach is motivated by our empirical analysis that shows three common syntactic patterns account for over 98% of the SRL annotations for both English and Chinese data. Based on this observation, we present a conversion scheme that packs SRL annotations into dependency tree representations through joint labels that permit highly accurate recovery back to the original format. This representation allows us to train statistical dependency parsers to tackle SRL and achieve competitive performance with the current state of the art. Our findings show the promise of syntactic dependency trees in encoding semantic role relations within their syntactic domain of locality, and point to potential further integration of syntactic methods into semantic role labeling in the future.

[pdf] [arXiv]

Bibtex

@inproceedings{shi-etal-2020-semantic,
    title = "Semantic Role Labeling as Syntactic Dependency Parsing",
    author = "Shi, Tianze  and
    Malioutov, Igor  and
    Irsoy, Ozan",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.emnlp-main.610",
    pages = "7551--7571",
}

Tianze Shi @ Cornell University. Built with jekyll