5th Year Master of Science in Computer Science Thesis Presentation
— 4:00pm
Location:
In Person
-
Traffic21 Classrooms, Gates Hillman 6501
Speaker:
IHITA MANDAL
,
Master's Student, Computer Science Department, Carnegie Mellon Univesrity
https://www.linkedin.com/in/ihita-mandal-3b8b51192?original_referer=https%3A//duckduckgo.com/
Task Extraction from Charts
Addressing the inaccessibility of data visualization is growing in prominence and importance in our field of work. Some attempts have been made to improve resources for practitioners or build more accessible visualization tooling or techniques. Despite these attempts, fundamental issues remain for addressing the growing scale of inaccessibility. To address scale, the most common technique is to use NLP and machine learning to automatically describe charts or produce analytical insights. While this growing body of automated description work holds promise, there are still many outstanding issues in this process.
In this project, I aim to provide insight into different aspects of a chart in the form of tasks and properties that may lend themselves to a useful description of the chart. I also specifically provide details on extracting information about contradictory data in the form of clusters from scatterplot charts, which tend to be a popular form of representing data. I also analyze how to effectively represent such data in a description, based on various factors such as cluster location and the proximity of the points within the cluster.
Thesis Committee:
Dominik Moritz (Chair)
Sherry Tongshuang Wu