Haoran (Felix) Xu

Haoran (Felix) Xu

NLPer

Johns Hopkins University

About Me

My wish is to fix the world of languages!

I will join Amazon Alexa AI as Applied Scientist Intern soon! I am a Ph.D. student in Computer Science at Johns Hopkins University, affiliated with the Center for Language and Speech Processing (CLSP), co-advised by Philipp Koehn and Kenton Murray. My most recent research focuses on Cross-lingual Transfer Learning and Machine Translation. I am also interested in applying Domain Adaptation to NLP tasks. Last summer, I joined the intern program at blab and worked on zero-shot cross-lingual information extraction under the supervision of Benjamin Van Durme and Mark Dredze. Prior to JHU, I was a research assistant working on Quadratic Programming with Mojtaba Soltanalian at UIC. Before starting my graduate study, I received the Winner Award in the 2018 Expo at UIC and the Best Research Paper Award at East China University of Science and Technology, focusing on Machine Learning and Pattern Recognition with the application to dynamic signature recognition.

Interests

  • Natural Language Processing
  • Computational Linguistics
  • Multilinguality
  • Machine Learning
  • Computer Vision

Education

  • Ph.D. in Computer Science, Present

    Johns Hopkins University

  • M.S. in Computer Science, 2020

    Johns Hopkins University

  • M.S. in Electrical and Computer Engineering, 2019

    University of Illinois at Chicago (3+2 Exchange Program)

  • B.E. in Information Engineering, 2018

    East China University of Science and Technology

Projects

*

Cross-Lingual Contextual Embedding Space Mapping

Proposed a novel method of contextual embedding mapping and revealed the tight relationship of isotropy, isometry and isomorphsim in contextual embedding spaces.

Efficient Quadratic Programming in Wireless Communication

Developed a new algorithm to reduce the peak energy of data transmission based on Unimodular Quadratic Programming.

Gradual Fine-Tuning for Low-Resource Domain Adaptation

Proposed novel data augmentation approach for domain adaptation, which surpasses state-of-the-art performance in Dialogue State Tracking and Event Extraction tasks.

Image expansion with GANs

Built a deep learning method based on GANs to naturally predict and expand the boundaries of incomplete images

Invisible Signature Security System

Designed a human-computer interaction GUI system to recognize signatures of users with high precision, where users sign their names in the air (invisibly).

Zero-Shot Cross-Lingual Dependency Parsing

Investigated a zero-shot approach for dependency parsing by building a multilingual concept-shared semantic space, which achieves state-of-the-art performance.