Biography

I’m a 2nd year PhD student in the Spoken Language Systems Group at MIT CSAIL, working with Dr. James Glass.

I am currently working on various projects on language and speech, including automatic fact-checking and end-to-end speech synthesis. I am generally interested in machine learning algorithms for natural language and speech, including but not limited to learning and analyzing representations, language understanding, and transfer learning for NLP and speech.

During my undergrad studies at National Taiwan University (NTU), I researched on speech and language understanding under Prof. Hung-Yi Lee and Prof. Lin-Shan Lee, and worked on machine learning problems for computer vision under Prof. Yu-Chiang Frank Wang at Academia Sinica/NTU. I also interned twice with the NLP team at Apple in California.

Here is my Curriculum Vitae (updated Sep 2019).

Interests

  • Natural Language Processing
  • Speech Processing
  • Machine Learning

Education

  • PhD Student in EECS, 2018 - Present

    Massachusetts Institute of Technology

  • BSE in Electrical Engineering, 2013 - 2018

    National Taiwan University

Experience

 
 
 
 
 

PhD Student

MIT CSAIL

Sep 2018 – Present Cambridge, MA, USA
Research Assistant in Spoken Language Systems group
 
 
 
 
 

NLP Intern

Apple Inc

Jul 2018 – Aug 2018 Cupertino, CA, USA
Research internship on NLP Team
 
 
 
 
 

NLP Intern

Apple Inc

Jun 2017 – Sep 2017 Cupertino, CA, USA
Research internship on NLP Team
 
 
 
 
 

Undergraduate Student

National Taiwan University (NTU)

Sep 2013 – Jan 2018 Taipei, Taiwan
  • Major in Electrical Engineering
  • Undergraduate Researcher in Speech Processing & Machine Learning Lab
  • Undergraduate Researcher in Vision & Learning Lab
  • Teaching Assistant for Machine Learning, Data Analytics & Modeling, and Signal & Systems

Projects

.js-id-deep-learning

Automatic Fact Checking

With the rapid increase of fake news in social media and its negative influence on people and public opinion, we present FAKTA, an unified framework for automatic fact checking that predicts the factuality of given claims and provides evidence at the document and sentence level to explain its predictions.

Multi-Label ZSL with Knowledge Graphs

Inspired by the way humans utilize semantic knowledge between objects of interests, we propose a novel deep learning framework that incorporates knowledge graphs for describing the relationships between multiple labels to achieve multi-label zero-shot learning (ML-ZSL).

Modular Chatbot

We built a modular dialogue system with deep learning techniques for the task of assisting people in department stores.

QA for TOEFL Listening Comprehension

Here is a short talk I gave on SPMLLab’s recent work on speech question answering in .

MasterView (VR System)

At the 2016 HackNTU Hackathon, our team developed MasterView, a virtual reality system that shows the expert’s moves in first-person perspective so the user can imitate and practice.

Slither.AR (AR Game)

Using common and well-known development tools, we transform slither.io, a game based on ‘Snake’, into an interactive augmented-reality game.

Large Scale Equivalence Checking and Functional Correction

In the 2015 CAD Contest, we developed a system to identify equivalent cuts in both equivalent and nonequivalent circuits for design partitioning.

Contact

  • weifang@mit.edu
  • Stata Center 32-G436, 32 Vassar St, Cambridge, MA, 02139, United States