In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy
will defend his proposal
Emphasis Selection For Textual Content
AbstractIn this proposal, we aim at creating a natural language processing system to select candidate words to emphasize. Word emphasis is used to convey specific meaning and attitude to readers by adding more aesthetic dimensions to the text. Whether it is colors, backgrounds, fonts, or styles like italic and boldface, it is used to effectively capture the intent of the sentence by removing the ambiguity that may exist in some plain texts. The ultimate goal of this research is to enable design assistance for the user during authoring by suggesting which part of the text to emphasize. Without knowing the author’s intent and only considering the input text, multiple emphasis selections are valid. We will investigate models that capture the inter-subjectivity in the audience as well as the ambiguity of the input. As part of this research, we will work on developing computational methods that aim to understand the most common interpretation of a written text, so the right emphasis can be achieved automatically or interactively. We will also introduce new data resources to evaluate the methods on different domains, from social media posts to presentation slides. Finally, we plan to release the implementation and data resources to facilitate future work relevant to this problem area.
Date: Wednesday, May 20, 2020
Time: 1:00 - 2:00 PM
Place: Online Presentation - Zoom Meeting
Advisor: Dr. Thamar Solorio
Faculty, students, and the general public are invited.