University of Illinois Urbana-Champaign

HiBi: A hierarchical bigram model for associative learning

Wang, Xiaoyan

Content Files
WANG-THESIS-2020.pdf

Permalink

https://hdl.handle.net/2142/108022

Description

Title
HiBi: A hierarchical bigram model for associative learning
Author(s)
Wang, Xiaoyan
Issue Date
2020-05-11
Director of Research (if dissertation) or Advisor (if thesis)
Zhai, Chengxiang
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Date of Ingest
2020-08-26T21:57:59Z
Keyword(s)
  • Natural language processing
  • Cognitive models
Abstract
There has been a shift of attention in the AI research where people gradually abandon traditional statistical models in favor of deep neural architectures. While effective in learning input-output mappings from two arbitrary distributions, the complex nature of neural models makes them hard to interpret. In this thesis, we introduce a more interpretable hierarchical bigram (HiBi) model, which is extended based on the simple bigram language model. It contains a few components inspired by theories of human cognition, and has been shown through experiments to be effective in learning meaningful representation from sequential inputs without any labeling. We hope that HiBi could be a starting point to develop more complex cognitive models that are both interpretable and effective for representation learning.
Graduation Semester
2020-05
Type of Resource
Thesis
Permalink
http://hdl.handle.net/2142/108022
Copyright and License Information
Copyright 2020 Xiaoyan Wang

Owning Collections

Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois
Dissertations and Theses - Computer Science
Dissertations and Theses from the Siebel School of Computer Science