Zongyi Liu
Pronouns: he/him/his
Research Mentor(s): Stefan Larson
Research Mentor School/College/Department: DryvIQ / NonUM
Program: UROP
Session: Session 6 (3:40pm – 4:30pm)
Authors:
Abstract
Today, the demand of methods to taxonomically or hierarchically classify of labels is increasingly growing, and traditional labor-intensive ways are already outdated and cannot fit today’s changes. To meet the demand, many scientists came up with different ways, and what we focus on is one of the problems of identifying and annotating collected documents and classify them later. We used many databases and distribute the work in the group to finish it collectively. Then we trained machine learning models on the data and evaluate performance. Finally we got the outcome, which is a paper detailing our dataset. This dataset will be a valuable resources for the academic community. Moreover, our finding would be very helpful for industries especially companies or organizations with demands to classify and categorize their datasets.
