Georgetown University LogoGeorgetown University Library LogoDigitalGeorgetown Home
    • Login
    View Item 
    •   DigitalGeorgetown Home
    • Georgetown University Institutional Repository
    • Georgetown College
    • Department of Linguistics
    • Graduate Theses and Dissertations - Linguistics
    • View Item
    •   DigitalGeorgetown Home
    • Georgetown University Institutional Repository
    • Georgetown College
    • Department of Linguistics
    • Graduate Theses and Dissertations - Linguistics
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Linguistic Interpretability and Composition of Abstract Meaning Representations

    Cover for Linguistic Interpretability and Composition of Abstract Meaning Representations
    View/Open
    View/Open: Blodgett_georgetown_0076D_15041.pdf (1.3MB) Bookview

    Creator
    Blodgett, Austin J
    Advisor
    Schneider, Nathan
    ORCID
    0000-0002-1285-1190
    Abstract
    Many Natural Language Processing (NLP) and Natural Language Understanding (NLU) tasks require some implicit representation of meaning. Abstract Meaning Representation (AMR; Banarescu et al., 2013) aims to be a scalable way of including explicit representations of meaning, in the form of semantic graphs. This work takes on a goal of augmenting AMR semantic graphs to be made linguistically interpretable---increasing the interpretability they add to a model.
     
    I pursue this goal through two avenues of research. First, I improve the analyzability of AMR via a novel, structurally comprehensive and linguistically enriched set of AMR-to-text alignments. I present this new formulation of AMR alignment which addresses a wide variety of linguistic phenomena, as well as a corpus of automatically generated alignments for English sentences, and a probabilistic, structure-aware alignment algorithm which produces alignments without supervision and with higher coverage, accuracy, and variety than alignments from existing AMR aligners.
     
    Second, I improve the compositionality of AMR via an extension of Combinatory Categorial Grammar (CCG) which allows AMR semantics and compositional derivation of AMR graphs. This formulation of AMR as graph semantics in CCG and accompanying combinatorial rules of CCG allow derivation of a full AMR graph in an interpretable way. Lastly, I conduct an empirical analysis of the compatibility and structural similarity/dissimilarity of AMR with automatically generated CCG parse data, and identify linguistic sources of complexity for the benefit of future research.
     
    Description
    Ph.D.
    Permanent Link
    http://hdl.handle.net/10822/1062665
    Date Published
    2021
    Subject
    AMR; CCG; explainability; interpretability; semantic graph; semantic parsing; Linguistics; Computer science; Linguistics; Computer science;
    Type
    thesis
    Publisher
    Georgetown University
    Extent
    193 leaves
    Collections
    • Graduate Theses and Dissertations - Linguistics
    Metadata
    Show full item record

    Georgetown University Seal
    ©2009 - 2022 Georgetown University Library
    37th & O Streets NW
    Washington DC 20057-1174
    202.687.7385
    digitalscholarship@georgetown.edu
    Accessibility
     

     

    Browse

    All of DigitalGeorgetownCommunities & CollectionsCreatorsTitlesBy Creation DateThis CollectionCreatorsTitlesBy Creation Date

    My Account

    Login

    Statistics

    View Usage Statistics

    Georgetown University Seal
    ©2009 - 2022 Georgetown University Library
    37th & O Streets NW
    Washington DC 20057-1174
    202.687.7385
    digitalscholarship@georgetown.edu
    Accessibility