• Login
    View Item 
    •   DSpace@RPI Home
    • Rensselaer Libraries
    • RPI Theses Open Access
    • View Item
    •   DSpace@RPI Home
    • Rensselaer Libraries
    • RPI Theses Open Access
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    AI enabled foreign language immersion : technology and method to acquire foreign languages with AI in immersive virtual worlds

    Author
    Divekar, Rahul R.
    Thumbnail
    View/Open
    180337_Divekar_rpi_0185E_11747.pdf (16.40Mb)
    Other Contributors
    Hendler, James A.; Su, Hui; Zhou, Yalun (Helen); Kephart, Jeffrey O.; Fox, Peter A.;
    Date Issued
    2020-08
    Subject
    Computer science
    Degree
    PhD;
    Terms of Use
    This electronic version is a licensed copy owned by Rensselaer Polytechnic Institute, Troy, NY. Copyright of original work retained by author.;
    Metadata
    Show full item record
    URI
    https://hdl.handle.net/20.500.13015/2614
    Abstract
    Students who learn foreign languages have limited exposure to conversations in the target language as, by definition, a foreign language is the one that is not commonly spoken where they live. However, exposure to the target language is key to acquiring it. This gap is commonly filled by international foreign language immersion programs. International foreign language immersion programs enable a student to move temporarily to a foreign country for several months where opportunities to interact in the target language are ample. However, the overhead of moving to a foreign country makes foreign language education less accessible. This dissertation explores how extensions to state-of-the-art Artificial Intelligence (AI) integrated with Extended Reality (XR) can bring experiences like the ones found in international immersion programs to a student and help them acquire a foreign language; without requiring them to travel extensively.; Specifically, we articulate a pedagogical framework that involves learning a foreign language with AI in XR. We show how AI can be extended from its state-of-the-art and integrated with XR technology to enable the said pedagogical framework. The learning methodology and technology are novel and resulting interactions are unique in that they immerse students without requiring intrusive wearables thereby allowing long-term collaborative experiences in a virtual world where students can communicate multi-modally with several AI Agents and each other. We test the novel interactions to observe users' characteristics in Human-AI conversational interactions and solve key challenges. The resulting novel interactions with AI in XR environments contributed by this dissertation are shown to improve foreign language learners’ proficiency across vocabulary, listening, comprehension and conversation.; Extended Reality (XR) and Artificial Intelligence (AI) are two technologies that can bring these theories to life. Specifically, recent developments in XR make it possible to enable physical immersion by creating a sense of suspended disbelief. Whereas, social immersion can be brought by embodied AI Agents situated in the visual scenes and can hear, see and speak to students. We show that by bringing AI and XR together, we can create an experience that provides authentic conversational opportunities like the ones found in international immersion programs and thus improve students' target language proficiency.; To bring this experience to the students, we rely on two key theories --- Physical immersion and social immersion. Physical immersion lets the students feel as if they are somewhere else while social immersion gives them a context to practice their conversational skills.;
    Description
    August 2020; School of Science
    Department
    Dept. of Computer Science;
    Publisher
    Rensselaer Polytechnic Institute, Troy, NY
    Relationships
    Rensselaer Theses and Dissertations Online Collection;
    Access
    Users may download and share copies with attribution in accordance with a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License. No commercial use or derivatives are permitted without the explicit approval of the author.;
    Collections
    • RPI Theses Online (Complete)
    • RPI Theses Open Access

    Browse

    All of DSpace@RPICommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    Login

    DSpace software copyright © 2002-2022  DuraSpace
    Contact Us | Send Feedback
    DSpace Express is a service operated by 
    Atmire NV