A Pipeline-Based Task-Oriented Dialogue System on DSTC2 Dataset

Simple item page
dc.contributor.advisorNg, Vincent
dc.creatorPang, Yize
dc.date.accessioned2019-10-07T20:29:47Z
dc.date.available2019-10-07T20:29:47Z
dc.date.created2019-05
dc.date.issued2019-05
dc.date.submittedMay 2019
dc.date.updated2019-10-07T20:29:49Z
dc.description.abstractDialogue systems have attracted a lot of attention since some conversational products like Google Assistant and Amazon Echo smart speaker have achieved big successes recently. In this work, we try to build a pipeline-based task-oriented dialogue system, which is the core technology behind these famous products. Our system consists of three modules: a GLAD dialogue state tracker, a policy learning module and a response generation module. They are sequentially connected. The contributions of this work are two-fold. Firstly, we propose an effective approach to improve the controllability of language generation. The experimental results show that this strategy significantly increases the key information accuracy in the generated dialogue responses. Secondly, we introduce a practical method to build a taskoriented dialogue system. Compared to models that are completely based on neural networks, the modularity of our system helps convert a hard problem into several smaller ones that are more specific and easier to solve.
dc.format.mimetypeapplication/pdf
dc.identifier.urihttps://hdl.handle.net/10735.1/6965
dc.language.isoen
dc.rights©2019 Yize Pang
dc.subjectNatural language processing (Computer science)
dc.subjectPipelining (Electronics)
dc.subjectAutomatic speech recognition
dc.titleA Pipeline-Based Task-Oriented Dialogue System on DSTC2 Dataset
dc.typeThesis
dc.type.materialtext
thesis.degree.departmentComputer Science
thesis.degree.grantorThe University of Texas at Dallas
thesis.degree.levelMasters
thesis.degree.nameMSCS

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
ETD-5608-011-PANG-260234.30.pdf
Size:
1.77 MB
Format:
Adobe Portable Document Format
Description:
Thesis
Download

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download

Collections

UTD Theses and Dissertations