Yung-Sung Chuang

I am now an undergraduate student in Electrical Engineering at National Taiwan University. My research interest broadly covers the deep learning technique for natural language processing and speech processing. In particular, I aim to utilize the ability of machines to help people grasp large information in text/audio form in efficient ways. Towards this goal, I joined Speech Processing Lab supervised by Hung-Yi Lee and Machine Intelligence Understanding Lab supervised by Yun-Nung (Vivian) Chen. I received the NTU Presidential Award for top 5% students four times in 2018-2020, Irving T. Ho Memorial Scholarship in 2018 and 2019. Here is my Curriculum Vitae.

I will share some notes or articles during my study in my blog. Thanks for reading and taking the time to comment :)

Publications

$^\dagger$ indicates equal contribution.

L2KD Lifelong Language Knowledge Distillation
Yung-Sung Chuang, Shang-Yu Su, Yun-Nung Chen.
Accepted by EMNLP 2020 conference; arXiv Preprint https://arxiv.org/abs/2010.02123
DualInf Dual Inference for Improving Language Understanding and Generation
Yung-Sung Chuang, Shang-Yu Su, Yun-Nung Chen.
Accepted by Findings of EMNLP 2020; arXiv Preprint https://arxiv.org/abs/2010.04246
MDS A Study of Cross-Lingual Ability and Language-specific Information in Multilingual BERT
Chi-Liang Liu, Tsung-Yuan Hsu, Yung-Sung Chuang, Hung-Yi Lee.
Accepted by RepL4NLP at ACL 2020; arXiv Preprint https://arxiv.org/abs/2004.09205
SpeechBERT SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answering
Yung-Sung Chuang, Chi-Liang Liu, Hung-Yi Lee, Lin-shan Lee.
Accepted by Interspeech 2020; arXiv Preprint https://arxiv.org/abs/1910.11559
This work won Interspeech 2020 Travel Grant.
RCT-GenTowards Understanding of Medical Randomized Controlled Trials by Conclusion Generation
Alexander Te-Wei Shieh, Yung-Sung Chuang, Shang-Yu Su, Yun-Nung Chen.
In Proceedings of the 10th International Workshop on Health Text Mining and Information Analysis at EMNLP (LOUHI 2019)

Short Talks (in Mandarin)

Non-Autoregressive Conditional Sequence Modeling

Unsupervised Syntactic Parsing

         
         

Virtual Conference Videos (in English)

[INTERSPEECH 2020] SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answering

[EMNLP 2020] Lifelong Language Knowledge Distillation

         
         

Teaching

Teaching Assistant, Deep Learning for Human Language Processing, 2020 Spring (Prof, Hung-Yi Lee)

Current Research Topics

Projects

MIPS Speech Recognition for Impaired Speaker
Yung-Sung Chuang, Tsai-Lun Yang, Che-Ruei Hsu, Liang-Yuan Wu.
Final Project in Introduction to Biomedical Engineering 2020 Spring
Reducing WER from 80% to 20% for patient voice via personalized adaptation (in Mandarin).
NMLAB DPP: Decentralized Publishing Platform
Yung-Sung Chuang, Chung-Hao Chao, Siang-Ruei Wu.
Final Project in Networking and Multinmedia Lab 2020 Spring
A Decentralized Publishing Platform created with Blockchain and Etheruem smart contract.
MIPS Single-Cycle MIPS Processor Implementation in Verilog
Yung-Sung Chuang, Ren-Chu Wang.
Final Project in Computer Architecture 2019 Fall
Ranking 2nd place out of 44 groups by A*T value (Area x Clock Time)
ICCAD Rectilinear Polygon Operations for Physical Design
Siang-Ruei Wu, Yung-Sung Chuang.
Final Project in Algorithms 2019 Spring
ICCAD 2019 CAD Contest - Problem E (competition website)
MDDA Multi-Source Unsupervised Domain Adaptation Challenge
Yung-Sung Chuang, Chen-Yi Lan, Hung-Ting Chen, Chang-Le Liu.
Final Project in Deep Learning for Computer Vision 2019 Spring
CycleGAN Transformer-based CycleGAN Text Style Transfer
Yung-Sung Chuang.
Research Project in 2018 Fall
PyWordSeg Robust Chinese Word Segmentation with Contextualized Word Representations
Yung-Sung Chuang.
ArXiv Link: https://arxiv.org/abs/1901.05816
Pypi Link: https://pypi.org/project/pywordseg/
Final project in Digital Signal Processing 2018 Fall
BiParser BiLSTM Collocation Parser
Yung-Sung Chuang.
Intern work in Acadamia Sinica, 2018 Fall
MTRS Chinese Multi Turn Response Selection
Yung-Sung Chuang, Hsing-Chien Wang, Yi-Ting Hsieh.
Final Project in Machine Learning 2018 Spring
MTRS Big Two Game Environment and Agent in C++
Yung-Sung Chuang, Hsin Cheng.
Final Project in Computer Programming 2017 Fall

Honors

  • Dean’s list (4 times), Electrical Engineering Dept. at NTU, Spring ’18, Spring ’19, Fall ’19, Spring ’20
  • Irving T. Ho Memorial Scholarship (2 times), EECS at NTU, Fall ’18, Fall ’19
  • Travel Grant, INTERSPEECH 2020 conference, Sep. 2020
  • Appier Best Application Award, 2020 NTU CSIE Undergrad Special Research Exhibition, Jun. 2020
  • 2nd Place & Appier 1st Award, 2019 NTU CSIE Undergrad Special Research Exhibition, Jun. 2019
  • 2nd Place, 2019 NTUEE Undergraduate Innovation Award, Jun. 2019
  • 1st Place, 2018 H. Spectrum Demo Day (out of 21 teams), Jul. 2018
  • 1st Place, NCTS Health Hackathon 2018 (out of 18 teams), Jun. 2018
  • Top 8 Finalist, Microsoft Imagine Cup Taiwan National Final 2018, Apr. 2018
  • Best Tech Award & Microsoft Enterprise Award, MakeNTU 2018 (out of 50 teams), Mar. 2018
  • 1st place of Dept. of Transportation, HackNTU 2017 (out of 100+ teams), Jul. 2017

Competitions

NCTS Health Hackathon 2018

1st Placewith NT$120,000 (out of 18 teams) [News, Certificate]

  • A hackathon on organized byNational Center for Theoretical Sciences and Mount Sinai Health System, New York.
  • Proposed an improved system for doctors shifting in hospital — PRO (Patient Relay Optimizer) to help doctors grasp all infoabout patients, status, tasks at a glance, reducing the risk of information shifting incompletely.
  • Won the 1st place of 2018 H. Spectrum Demo Day (out of 21 teams) [News]

MakeNTU 2018

Best Tech Award with NT$50,000 & Microsoft Enterprise Award (out of 50 teams) [Photo]

  • A hackathon focus on the combination of hardware and software, organized by NTU
  • Built an automatic machine for picking good coffee beans with deep learning technique.
  • Placed intop 8in the finalist of Microsoft Imagine Cup Taiwan National Final 2018.

HackNTU 2017

1st Place of Department of Transportation with NT$50,000 (out of 100+ teams) [Photo]

  • Built asmart bus bell system for solving the problems of getting on the right bus in the huge and busy city.
  • Exhibited on WCIT 2017 (World Congresson Information Technology).