Si Wu

(She/her/hers)

PhD Student

Si Wu
  • Natural language processing
  • Unsupervised learning
  • Computational social science
  • Digital humanities
  • BS in Computer Engineering; University of California, San Diego

Si Wu is a doctoral student at the Khoury College of Computer Sciences at Northeastern University, advised by David Smith. Her doctoral research focuses on natural language processing and optical character recognition.

Before joining Khoury College in 2020, Wu attended the University of California, San Diego, where she studied style transfer in fonts, historical document processing, and flash memory error prediction. She also tutored for data structures, computer organization and systems programming, and Java programming courses. Wu collaborated on published papers there and at Northeastern, where she works in page layout analysis and machine translation.

Wu is fascinated by how humans communicate and connect through different media types, and wants to uncover and analyze ever-changing hidden structures and underlying patterns in human information exchange. She is affiliated with the NULab for Texts, Maps, and Networks.