Ying Shen

Ying Shen

Computer Science Phd Student

Virginia Tech

About

I am a PhD student of Computer Science at Virginia Tech. I am very fortunate to be advised by Prof. Lifu Huang and Prof. Ismini Lourentzou.

My research interests lie in deep learning, natural language processing and multi-modal machine learning, the vibrant multi-disciplinary research field that focuses on integrating and modeling multiple communicative modalities, including linguistic, acoustic and visual messages. My enthusiasm is to build more human-like interactive agents to better understand, interpret and reason about the world around us.

I obtained my Master of Science degree in Intelligent Information Systems from Carnegie Mellon University and my Bachelor’s degree from School of Software Engineering, Fudan University. Previously, I worked with Prof. Louis-Philippe Morency and Prof. Graham Neubig at CMU.

I am honored to have been awarded the Amazon-VT Fellowship for the 2023-2024 academic year.

Interests
  • Deep Learning
  • Natural Language Processing
  • Multimodal Machine Learning
  • Computer Vision
  • Deep Generative Models
Education
  • PhD in Computer Science, Present

    Virginia Tech

  • MSc in Intelligent Information Systems, 2018

    Carnegie Mellon University

  • BEng in Software Engineering, 2017

    Fudan University

Experience

 
 
 
 
 
Machine Learning Research Intern
May 2023 – Aug 2023 New York, NY
 
 
 
 
 
Research Associate
Jan 2019 – Dec 2019 Pittsburgh, PA
 
 
 
 
 
Graduate Research Assistant
Sep 2017 – Dec 2018 Pittsburgh, PA
 
 
 
 
 
Research Intern
Aug 2016 – Jul 2016 Pittsburgh, PA

Projects

Improving Machine Translation Quality by Cross-lingual Natural Language Inference

Improving Machine Translation Quality by Cross-lingual Natural Language Inference

An efficient method to integrate multiple unimodal representations (e.g. verbal, visual and audio) into one compact multimodal representation.

Dependency Parsing with Deep Reinforcement Learning

Dependency Parsing with Deep Reinforcement Learning

A reinforcement learning agent to perform non-greedy decoding with transition-based dependency parser by considering the future rewards.

WORDS CAN SHIFT

WORDS CAN SHIFT

Dynamically Adjusting Word Representations Using Nonverbal Behaviours.

Efficient Low-rank Multimodal Fusion With Modality-Specific Factors

Efficient Low-rank Multimodal Fusion With Modality-Specific Factors

An efficient method to integrate multiple unimodal representations (e.g. verbal, visual and audio) into one compact multimodal representation.

SARA: the Socially Aware Robot Assistant

SARA: the Socially Aware Robot Assistant

SARA is a socially-aware robot assistant that can interact with people through personalizing the interaction.

A little more about me

  • I love painting. To me, painting is like another medium (besides verbal and nonverbal behaviors) for expressing feelings and thoughts.

  • I enjoy traveling, exploring new restaurants, watching Japanese animations, and swimming.

  • I can speak Shanghainese (native), Chinese Mandarin (native), English (fluent), and Japanese (conversational).

  • I hope to use technology to help minority groups and improve people’s quality of life.

“There is only one heroism in the world: to see the world as it is, and to love it.”

– Romain Rolland