Index Catalog // ScholarsArchive@OSU

Start Over

Filtering by: Date issued sim 2019-06-20 Rights Statement In Copyright

Learning with Limited Labeled Data in Natural Language Processing

Creator:

Obeidat, Rasha

Abstract:

The advent of deep learning models leads to a substantial improvement in a wide range of NLP tasks, achieving state-of-art performances without any hand-crafted features. However, training deep models requires a massive amount of labeled data. Labeling new data as a new task or domain emerges consumes time and efforts...

Resource Type:

Dissertation