Date of Award
1-1-2019
Document Type
Thesis
Degree Name
M.S. in Engineering Science
First Advisor
Naeemul Hassan
Second Advisor
Yixin Chen
Third Advisor
Kristen A. Swain
School
University of Mississippi
Relational Format
dissertation/thesis
Abstract
This study introduces a new Natural Language Generation (NLG) task – Unit Claim Identification. The task aims to extract every piece of verifiable information from a headline. The Unit Claim identification has applications in other domains; such as fact-checking where the identification of each verifiable information from a check-worthy statement can lead to an effective fact-check. Moreover, the extracting of the unit claims from headlines can identify a misleading news article, by mapping evidence from contents. For addressing the unit claim identification problem, we outlined a set of guidelines for data annotation, arranged in-house training for the annotators and obtained a small dataset. We explored two potential approaches - 1) Rule-based approach and 2) Deep learning-based approach and compared their performances. Although the performance of the deep learning-based approach was not very effective due to small number of training instances, the rule-based approach shoa promising result in terms of precision (65.85%).
Recommended Citation
Rony, Md Main Uddin, "Towards Misleading Connection Mining" (2019). Electronic Theses and Dissertations. 1940.
https://egrove.olemiss.edu/etd/1940