Abstract
dc:description.abstractThe ability to determine the underlying document structure of Electronic Theses and Dissertations (ETDs) can facilitate the development of many services. Some of these include summarizing long documents, semantic parsing, classification, and indexing for discovery. This thesis puts forward a bottom-up approach to segmenting ETDs and shows that LaTeX manipulation can be used to help create meaningful data sets. The research provides two data sets. The first contains 1,459 ETDs plus the chapter boundaries generated using our Chapter-Segmentation Pipeline. The second is a data set containing 150 ETDs with manually labelled chapter boundaries. This research also involves training deep learning models using our data sets. Overall, the goals of this research are to encourage researchers within the natural language processing community to incorporate the power of LaTeX manipulation to create more data sets, and to increase ETD accessibility.
Degree
thesis:*- Name thesis:degree_name
- Master of Science
- Level thesis:degree_level
- masters
- Discipline thesis:degree_discipline
- Computer Science and Applications
- Department dc:contributor.department
- Computer Science and Applications
- Grantor dc:publisher
- Virginia Tech
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Manzoor, Javaid Akbar
- Chair dc:contributor.committeechair
-
- Fox, Edward A.
- Committee members dc:contributor.committeemember
-
- Wu, Jian
- Heath, Lenwood S.
Subjects
dc:subject × 5Rights
dc:rights- Statement dc:rights
-
- In Copyright
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Dc Identifier Other
- vt_gsexam:35736