Skip to main navigation Skip to search Skip to main content

End-to-end mBERT based Seq2seq Enhanced Dependency Parser with Linguistic Typology knowledge

    • University of Galway

    Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

    3 Citations (Scopus)

    Abstract

    We describe the NUIG solution for IWPT 2021 Shared Task of Enhanced Dependency (ED) parsing in multiple languages. For this shared task, we propose and evaluate an End-to-end Seq2seq mBERT- based ED parser which predicts the ED-parse tree of a given input sentence as a relative head-position tag-sequence. Our proposed model is a multitasking neural-network which performs five key tasks simultaneously namely UPOS-tagging, UFeat-tagging, Lemmatization, Dependency-parsing and ED-parsing. Furthermore we utilise the linguistic typology available in the WALS database to improve the ability of our proposed end-to-end parser to transfer across languages. Results show that our proposed Seq2seq ED-parser performs on par with state-of-the-art ED-parser despite having a much simpler design.

    Original languageEnglish
    Title of host publicationProceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies, IWPT 2021
    EditorsStephan Oepen, Kenji Sagae, Reut Tsarfaty, Gosse Bouma, Djame Seddah, Daniel Zeman
    PublisherAssociation for Computational Linguistics (ACL)
    Pages225-232
    Number of pages8
    ISBN (Electronic)9781954085800
    Publication statusPublished - 2021
    Event17th International Conference on Parsing Technologies, IWPT 2021 - Hybrid, Bangkok, Thailand
    Duration: 6 Aug 20216 Aug 2021

    Publication series

    NameProceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies, IWPT 2021

    Conference

    Conference17th International Conference on Parsing Technologies, IWPT 2021
    Country/TerritoryThailand
    CityHybrid, Bangkok
    Period6/08/216/08/21

    Fingerprint

    Dive into the research topics of 'End-to-end mBERT based Seq2seq Enhanced Dependency Parser with Linguistic Typology knowledge'. Together they form a unique fingerprint.

    Cite this