Self-training for unsupervised parsing with PRPN

Anhad Mohananey, Katharina Kann, Samuel R. Bowman

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Neural unsupervised parsing (UP) models learn to parse without access to syntactic annotations, while being optimized for another task like language modeling. In this work, we propose self-training for neural UP models: we leverage aggregated annotations predicted by copies of our model as supervision for future copies. To be able to use our model's predictions during training, we extend a recent neural UP architecture, the PRPN (Shen et al., 2018a), such that it can be trained in a semi-supervised fashion. We then add examples with parses predicted by our model to our unlabeled UP training data. Our self-trained model outperforms the PRPN by 8.1% F1 and the previous state of the art by 1.6% F1. In addition, we show that our architecture can also be helpful for semi-supervised parsing in ultra-lowresource settings.

    Original languageEnglish (US)
    Title of host publicationIWPT 2020 - 16th International Conference on Parsing Technologies and IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, Proceedings of the Conference
    PublisherAssociation for Computational Linguistics (ACL)
    Pages105-110
    Number of pages6
    ISBN (Electronic)9781952148118
    StatePublished - 2020
    Event16th International Conference on Parsing Technologies, IWPT 2020, co-located with the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 - Virtual, Online, United States
    Duration: Jul 9 2020 → …

    Publication series

    NameProceedings of the Annual Meeting of the Association for Computational Linguistics
    ISSN (Print)0736-587X

    Conference

    Conference16th International Conference on Parsing Technologies, IWPT 2020, co-located with the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
    Country/TerritoryUnited States
    CityVirtual, Online
    Period7/9/20 → …

    ASJC Scopus subject areas

    • Computer Science Applications
    • Linguistics and Language
    • Language and Linguistics

    Fingerprint

    Dive into the research topics of 'Self-training for unsupervised parsing with PRPN'. Together they form a unique fingerprint.

    Cite this