Deep Generation Techniques in Task-Oriented Dialogue Systems

by Shu, Lei

Type Thesis
Rate 0.0 /5

Building a task-oriented dialogue system like a restaurant booking is meaningful since it can largely reduce the working load of human and serve multiple users at the same time. A task-oriented dialogue system is often composed of a few modules, such as natural language understanding, dialogue state tracking, knowledgebase (KB) query, dialogue policy engine and response generation. Language understanding aims to convert the input to some predefined semantic frame. State tracking models explicit…

Read More ↓
Details
Files
Reviews
Download

Summary

Building a task-oriented dialogue system like a restaurant booking is meaningful since it can largely reduce the working load of human and serve multiple users at the same time. A task-oriented dialogue system is often composed of a few modules, such as natural language understanding, dialogue state tracking, knowledgebase (KB) query, dialogue policy engine and response generation. Language understanding aims to convert the input to some predefined semantic frame. State tracking models explicitly the input semantic frame and the dialogue history for producing KB queries. Dialogue policy model decides on the system action which is then realized by a natural language generation component.

Read More ↓

Edition Statements

  • Publication Date:2020

Thesis Information

  • Degree:Ph.D.
  • University:University of Illinois at Chicago
  • Advisor/Supervisor:Liu, Bing
  • Pages:209

Publication Statements

  • Language:eng
  • Publication Date:2020

Edition Identifiers

  • proquest:2518766618

Subjects

Computer Science Deep neural network dialogue system eng Generation lifelong learning natural language generation natural language understanding Open-world learning PDF Sentiment analysis

Writers

Shu, Lei Liu, Bing

Rate & Review

0.0/5
(0 people Voted)

No reviews yet. Be the first to rate this work.

Files & Downloads

Log in to request a copy