| CARVIEW |
Eddy (Pei-Hao) Su
About
I co-founded PolyAI in 2017 to develop conversational AI platform for Enterprise-Ready Voice Assistants.
I obtained my PhD in Statistical Spoken Dialogue Systems at Cambridge University supervised by Professor Steve Young. My PhD was funded by Taiwan Cambridge Scholarship, and I was a member of Queens' College. I was also fortunate to work with Dr. Yuandong Tian at Facebook AI Research in the last summer of my PhD.
My primary research interest lies mainly in the intersection of deep learning and reinforcement learning for spoken dialogue systems, aiming to set up an unified framework for language understanding/replying and a system that is capable of scaling to broad domains and directly learn from human user interaction.
Prior to Cambridge, I received my Bachelor and Master degree in EECS from National Taiwan University, where I joined the Digital Speech Processing Laboratory held by Professor Lin-shan Lee and focused on statistical dialogue modelling for personalising pronunciation training in a dialogue game.
Timeline
Awards
- Company of the Year, Cambridge Computer Lab Ring, 2019
- Best Student Paper Award, ACL, 2016
- W. G. Collins Endowment Fund Award, Cambridge University Engineering Dept., 2016
- Interspeech Travel Grant, ISCA, 2015
- Taiwan Cambridge Scholarship, Cambridge Trust & MOE of Taiwan, 2014-17
- Government Scholarship for Studying Abroad (waived), MOE of Taiwan, 2014
- ICASSP Travel Grant, National Science Council of Taiwan, 2013
- Advanced Speech Technologies Scholarship, NTU EECS Department, 2012
- Best Intern, Trend Micro Inc., 2012
- Dean's List, NTU, 2008
Selected Publications
First author and main work only. See my Google Scholar page for full list.
PhD Thesis
- "Reinforcement Learning and Reward Estimation for Dialogue Policy Optimisation", PhD Thesis, University of Cambridge. [PDF] [bib]
Journal Articles
- "Reward estimation for dialogue policy optimisation", Computer Speech & Language, Volume
51, September 2018. [PDF] [bib]
Pei-Hao Su, Milica Gašić, and Steve Young - "A Recursive Dialogue Game for Personalized Computer-Aided Pronunciation Training", IEEE
Transaction on Audio, Speech and Language Processing, January 2015. [PDF] [bib]
Pei-hao Su, Chuan-hsun Wu, and Lin-shan Lee
Conference Papers
- "On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems", ACL
2016. (Best Student Paper Award)
[PDF] [bib] [slides] [data] [video]
Pei-Hao Su, Milica Gašić, Nikola Mrkšić, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen and Steve Young - "Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken
Dialogue Systems", SIGDIAL 2015. [PDF] [bib]
Pei-Hao Su, David Vandyke, Milica Gašić, Nikola Mrkšić, Tsung-Hsien Wen and Steve Young - "Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning
in Spoken Dialogue Systems", Interspeech 2015. [PDF] [bib]
Pei-Hao Su, David Vandyke, Milica Gašić, Dongho Kim, Nikola Mrkšić, Tsung-Hsien Wen and Steve Young
Featured Talks
Tutorial
- "Deep Learning for Conversational AI", NAACL 2018 tutorial. [Website]
Selected Invited Talks
- "Practical Approaches to Conversational AI", ODSC 2018
- "Reward Estimation for Dialogue Policy Optimisation", DeepHack.Turing Summer School Hackathon, Moscow, Russia, 2017. [slides]
- "Beyond Siri: towards fully data-driven conversational systems", Queens' College Cambridge Grad Talk, 2017
- "Practical Human-in-the-loop Reinforcement Learning in Spoken Dialogue Systems", Apple Cambridge, 2016
Teaching
- Spring 2017: MPhil Project Supervision on Sample-efficient Reinforcement Learning for Dialogue Management, Cambridge University
- Spring 2017: Reinforcement Learning, MPhil in Machine Learning, Speech and Language Technology, Cambridge University
- Fall 2016: Introduction to Python, Murray Edwards College, Cambridge University
- Spring 2016: Statistical Dialogue Systems, MPhil in Machine Learning, Speech and Language Technology, Cambridge University
- 2012-2013: Digital Speech Processing, EECS Department, National Taiwan University
Contact
Email: eddy@poly.ai