Hi! I'm Ralph.


I'm a first-year PhD at the University of Waterloo under the supervision of Jimmy Lin. I'm also mentored by Lili, Ferhan, and Yaoliang. I work at the junction of natural language processing, speech recognition, and deep learning.

My overall research direction is in improving the efficiency of humans, machines, and everything in between. How do we learn parsimonious representations of data? What are sources of user inefficiency in productionized models? How do we accelerate large neural networks? Those are a few questions that I explore.

Papers

2019
Natural Language Generation for Effective Knowledge Distillation
Raphael Tang, Yao Lu, Jimmy Lin
EMNLP-IJCNLP 2019 DeepLo Workshop
Incorporating Contextual and Syntactic Structures Improves Semantic Similarity Modeling
Linqing Liu, Wei Yang, Jinfeng Rao, Raphael Tang, Jimmy Lin
EMNLP-IJCNLP 2019
Honkling: In-Browser Personalization for Ubiquitous Keyword Spotting
Jaejun Lee, Raphael Tang, Jimmy Lin
EMNLP-IJCNLP 2019 Demo
Challenges and Opportunities in Understanding Spoken Queries Directed at Modern Entertainment Platforms
Ferhan Ture, Jinfeng Rao, Raphael Tang, Jimmy Lin
SIRIP 2019
DocBERT: BERT for Document Classification
Ashutosh Adhikari, Achyudh Ram, Raphael Tang, Jimmy Lin
arXiv
Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
Raphael Tang*, Yao Lu*, Linqing Liu*, Lili Mou, Olga Vechtomova, Jimmy Lin
arXiv
*Equal contribution.
Yelling at Your TV: An Analysis of Speech Recognition Errors and Subsequent User Behavior on Entertainment Systems
Raphael Tang, Ferhan Ture, Jimmy Lin
SIGIR 2019
Universal Voice-Enabled User Interfaces using JavaScript
Jaejun Lee, Raphael Tang, Jimmy Lin
IUI 2019 Demo
Rethinking Complex Neural Network Architectures for Document Classification
Ashutosh Adhikari*, Achyudh Ram*, Raphael Tang, Jimmy Lin
NAACL 2019
*Equal contribution.
2018
Streaming Voice Query Recognition Using Causal Convolutional Recurrent Neural Networks
Raphael Tang, Gefei Yang, Hong Wei, Yajie Mao, Ferhan Ture, Jimmy Lin
arXiv
FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks
Raphael Tang, Ashutosh Adhikari, Jimmy Lin
NIPS 2018 Workshop on Compact Deep Neural Networks with Industrial Applications
Progress and Tradeoffs in Neural Language Models
Raphael Tang, Jimmy Lin
arXiv
JavaScript Convolutional Neural Networks for Keyword Spotting in the Browser: An Experimental Analysis
Jaejun Lee, Raphael Tang, Jimmy Lin
arXiv
Adaptive Pruning of Neural Language Models for Mobile Devices
Raphael Tang, Jimmy Lin
arXiv
An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting
Raphael Tang, Weijie Wang, Zhucheng Tu, Jimmy Lin
ICASSP 2018
Deep Residual Learning for Small-Footprint Keyword Spotting
Raphael Tang, Jimmy Lin
ICASSP 2018
2017
Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting
Raphael Tang, Jimmy Lin
arXiv

Work Experience

Research Contractor
Comcast
Oct 2018–Present
  • Conduct research on improving voice query search on the X1 enter-tainment platform.
Research Intern
Comcast
May 2018–Aug 2018
  • Designed speech recognition model currently in production to serve millions of voice queries per day on the X1 entertainment platform.
  • Worked with team to code, test, and deploy the system.
Software Developer
Vitameter
Aug 2014–Aug 2015
  • Envisioned, designed, and programmed Android application.
  • Designed $25,000- and $10,000-winning pitch and video.

Projects