Graduate Thesis Or Dissertation
Natural Language Processing with Hierarchical Neural Network Models Public Deposited
https://scholar.colorado.edu/concern/graduate_thesis_or_dissertations/8623hz08w
- Abstract
Unsupervised training has recently been successfully used to enhance the performance of neural networks. To understand the advantage provided by the structure of unsupervised pre trained models, a network theory based analysis of word representation similarities was performed, revealing the structure discovered by unsupervised models trained on a large english language corpus. A Part of Speech Tagger and two versions of Semantic Role Labelers were defined and tested to explore architectural configurations and training strategies. In order to thoroughly test various Neural Network Natural Language Models, a highly configurable software implementation was developed.
- Creator
- Date Issued
- 2014
- Academic Affiliation
- Advisor
- Committee Member
- Degree Grantor
- Commencement Year
- Subject
- Last Modified
- 2020-05-13
- Resource Type
- Rights Statement
- Language
Relationships
Items
| Thumbnail | Title | Date Uploaded | Visibility | Actions |
|---|---|---|---|---|
|
|
foland.pdf | 2020-05-13 | Public | Download |