Exploring the Reformulation of NLP Tasks as Text Generation Tasks

dc.contributor.advisorNguyen, Thien
dc.contributor.authorHasan, Rasti
dc.date.accessioned2022-10-04T19:38:01Z
dc.date.available2022-10-04T19:38:01Z
dc.date.issued2022-10-04
dc.description.abstractIn recent years, NLP classification tasks have been reformulated as text generation tasks in the form of text-to-text transformer-based models that achieve state-of-the-art performance by better utilizing pre-trained language models. This work provides a historical background, a taxonomy based on the output structures of these methods, an exploration of aspects of such models with several representative works, and discusses the current state and future of these models.en_US
dc.identifier.urihttps://hdl.handle.net/1794/27594
dc.language.isoen_US
dc.publisherUniversity of Oregon
dc.rightsAll Rights Reserved.
dc.subjectGenerative Modelsen_US
dc.subjectNatural Language Processingen_US
dc.titleExploring the Reformulation of NLP Tasks as Text Generation Tasks
dc.typeElectronic Thesis or Dissertation
thesis.degree.disciplineDepartment of Computer and Information Science
thesis.degree.grantorUniversity of Oregon
thesis.degree.levelmasters
thesis.degree.nameM.S.

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Hasan_oregon_0171N_13323.pdf
Size:
582.5 KB
Format:
Adobe Portable Document Format