Training and architecting sequence to sequence language models for applications in varied domains

Authors
Li, Congrui
ORCID
Loading...
Thumbnail Image
Other Contributors
Fox, Peter A.
Hendler, James A.
Bennett, Kristin P.
Kuruzovich, Jason N.
Issue Date
2019-05
Keywords
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.
Full Citation
Abstract
This thesis introduces three innovative case studies using variants of seq2seq model, and each of them focuses on a different stage of the model's training process.
Description
May 2019
School of Science
Department
Dept. of Computer Science
Publisher
Rensselaer Polytechnic Institute, Troy, NY
Relationships
Rensselaer Theses and Dissertations Online Collection
Access
Restricted to current Rensselaer faculty, staff and students. Access inquiries may be directed to the Rensselaer Libraries.