Zejiang Shen is a data science and deep learning researcher. He is a Predoctoral Young Investigator at Allen Institute of AI (AI2), interested in using layouts to better understand various document data.
Before joining AI2, Zejiang Shen was a Data Science Fellow at the Institute for Quantitative Social Science (IQSS) at Harvard University. He worked closely with Prof. Melissa Dell using deep learning tools to distill important economic information from historical scans and analyze the extracted text.
He obtained his master’s degree from Data Science Initiative (DSI) at Brown University. He was supervised by Prof. James Tompkin on several image translation and generation projects using Generative Adversarial Nets (GAN).
Joined in AI2 as a Predoctoral Young Investigator.
Our recent paper OLALA: Object-Level Active Learning Based Layout Annotation was released on arxiv.
We built a new library Layout-Parser for general-purpose document layout parsing.