• Find People
  • Campus Map
  • PiratePort
  • A-Z
    • About
    • Submit
    • Browse
    • Login
    View Item 
    •   ScholarShip Home
    • Dissertations and Theses
    • Master's Theses
    • View Item
    •   ScholarShip Home
    • Dissertations and Theses
    • Master's Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of The ScholarShipCommunities & CollectionsDateAuthorsTitlesSubjectsTypeDate SubmittedThis CollectionDateAuthorsTitlesSubjectsTypeDate Submitted

    My Account

    Login

    Statistics

    View Google Analytics Statistics

    A FRAMEWORK FOR QUESTION ANSWERING SYSTEM USING DYNAMIC CO-ATTENTION NETWORKS

    Thumbnail
    View/ Open
    Busireddy_Thesis_spring2020.pdf (1.147Mb)

    Show full item record
    Author
    Busireddy, Swetha
    Abstract
    Question answering (QA) systems have evolved exponentially over the past few years and have reached a reliable human standard. Attention mechanisms, as well as other methods of deep learning, paved the way for this development. But, because of their single-pass nature, they are incapable of recovering from local maxima matching to incorrect answers. Dynamic coattention network (DCN) is used to answer this issue. But as it has only one layer, the ability of the DCN to write diverse input representations is limited. We proposed a few modifications to DCN to overcome these findings. First, we used a bidirectional long short-term memory network (biLSTM) to encode the question and document. Next, we applied the concept of self-attention to DCN by using multiple coattention layers. This helps the encoder to generate more profuse input representations. Lastly, we combine outputs from these layers; this improves the long-range dependencies. We built a question answering system based on this multiattention DCN and tested on one of our course documents. On Stanford question answering dataset (SQuAD), this system improves the F1 mean on validation to 79.9% from its previous state of art at 75.6%.
    URI
    http://hdl.handle.net/10342/8646
    Date
    2020-06-22
    Citation:
    APA:
    Busireddy, Swetha. (June 2020). A FRAMEWORK FOR QUESTION ANSWERING SYSTEM USING DYNAMIC CO-ATTENTION NETWORKS (Master's Thesis, East Carolina University). Retrieved from the Scholarship. (http://hdl.handle.net/10342/8646.)

    Display/Hide MLA, Chicago and APA citation formats.

    MLA:
    Busireddy, Swetha. A FRAMEWORK FOR QUESTION ANSWERING SYSTEM USING DYNAMIC CO-ATTENTION NETWORKS. Master's Thesis. East Carolina University, June 2020. The Scholarship. http://hdl.handle.net/10342/8646. September 25, 2023.
    Chicago:
    Busireddy, Swetha, “A FRAMEWORK FOR QUESTION ANSWERING SYSTEM USING DYNAMIC CO-ATTENTION NETWORKS” (Master's Thesis., East Carolina University, June 2020).
    AMA:
    Busireddy, Swetha. A FRAMEWORK FOR QUESTION ANSWERING SYSTEM USING DYNAMIC CO-ATTENTION NETWORKS [Master's Thesis]. Greenville, NC: East Carolina University; June 2020.
    Collections
    • Computer Science
    • Master's Theses
    Publisher
    East Carolina University

    xmlui.ArtifactBrowser.ItemViewer.elsevier_entitlement

    East Carolina University has created ScholarShip, a digital archive for the scholarly output of the ECU community.

    • About
    • Contact Us
    • Send Feedback