Si Wu （吴斯） Pronouns: she/her/hers
Khoury College of Computer Science, Northeastern University
Second-year Ph.D. student
Advisor: Prof. David A. Smith
Research Interests: natural language processing, unsupervised learning, computational social science, and digital humanities.
I’ve always been fascinated by how human beings communicate and build connections using different types of media. I am interested in uncovering the hidden structures and underlying patterns in human information exchange, in particular, how they develop and change over time.
At Northeastern: page layout analysis and machine translation.
Publications(Google Scholar link)
Latest to oldest:
(* indicates equal contribution)
"Scalable Font Reconstruction with Dual Latent Manifolds" Nikita Srivatsan, Si Wu, Jonathan Barron, and Taylor Berg-Kirkpatrick. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021 (pdf)
"Digital Editions as Distant Supervision for Layout Analysis of Printed Books" *Alejandro Toselli, *Si Wu, and *David A. Smith. In Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2021 (link from Springer)
"Bad Page Detector for NAND Flash Memory" Yi Liu, Si Wu, and Paul H. Siegel. Non-Volatile Memories Workshop, 2020 (pdf)
"Quantifying Gaze Behavior During Real World Interactions Using Automated Object, Face, and Fixation Detection" Leanne Chukoskie, Shengyao Guo, Eric Ho, Yalun Zheng, Qiming Chen, Vivian Meng, John Cao, Nikhita Devgan, Si Wu, and Pamela C. Cosman. IEEE Transactions on Cognitive and Developmental Systems, 2018 (pdf)
- CSE 100: Advanced Data Structures (Winter 2019, Spring 2019, UCSD)
- CSE 30: Computer Organization and Systems Programming (Fall 2019, UCSD)
- CSE 8B: Java Programming II (Spring 2018, UCSD)
- Splash @ UCSD 2019: Build My First Website
Northeastern University (2020 - Present)
Ph.D. in Computer Science
I love stories and storytelling of all forms. I am particularly interested in film, singing, and photography.