Shuoyang Ding bio photo

Shuoyang Ding

At Longwood Gardens, PA. November 2016.

Email Facebook Github

About

I'm a PhD student candidate in the Department of Computer Science, Johns Hopkins University. As a member of Center for Language and Speech Processing, I'm currently involved in research on neural machine translation. Yet personally, I'm interested in problems of different categories in the field of natural language processing. My advisors is Philipp Koehn.

Before joining Johns Hopkins, I got my Bachelor's degree in Beijing University of Posts & Telecommunications. During the last year of my undergraduate study, I worked with Weiwei Sun in the Language Computing and Web Mining Group of Institute of Computer Science & Technology, Peking University, with a focus on semantic parsing and Chinese word segmentation.

News

  • June 2018: Our Interspeech 2018 paper on Data Augmentation for End-to-End ASR was nominated for the ISCA Best Student Paper Award.
  • May 2018: I am doing a deep learning research internship this summer with Salesforce Research (previously MetaMind).

Courses

Teaching

Publications

  • Multi-Modal Data Augmentation for End-to-end ASR | Adithya Renduchintala, Shuoyang Ding, Matthew Wiesner, Shinji Watanabe, Interspeech 2018 (To Appear) [pdf]
  • The JHU Machine Translation Systems for WMT 2017 | Shuoyang Ding, Huda Khayrallah, Philipp Koehn, Matt Post, Gaurav Kumar, and Kevin Duh, WMT 2017 [pdf]
  • The JHU Machine Translation Systems for WMT 2016 | Shuoyang Ding, Kevin Duh, Huda Khayrallah, Philipp Koehn, and Matt Post, WMT 2016 [pdf]
  • Grammatical Relations in Chinese:GB-Ground Extraction and Data-Driven Parsing | Weiwei Sun, Yantao Du, Xin Kou, Shuoyang Ding, Xiaojun Wan, ACL 2014 [pdf]

Preprints

  • How Do Source-side Monolingual Word Embeddings Impact Neural Machine Translation? | Shuoyang Ding and Kevin Duh, 2018 [pdf]
  • Backstitch: Counteracting Finite-sample Bias via Negative Steps | Yiming Wang, Hossein Hadian, Shuoyang Ding, Ke Li, Hainan Xu, Xiaohui Zhang, Daniel Povey, Sanjeev Khudanpur, 2017 [pdf]