ZHAO Tianyu - homepage

ZHAO Tianyu 趙天雨

Github Page | Google Scholar | Resume

Address: Shibuya 2-24-12 39F WeWork, Shibuya-ku, Tokyo 150-6139, JAPAN
E-mail: zhaoty.ting[at]gmail.com



I have joined rinna Co., Ltd as a researcher from October 2020.
I apply NLP techniques to building new generation dialogue systems.
I speak pretty good Madarin Chinese, moderately good English, and not quite good Japanese.
I play billiard, and I play guitar in a band named Shanghai Shy Orchestra.

Research Topics

Natural Language Processing, Dialogue, Machine Learning


Work Experience

2020.10 - Present
Researcher @ rinna Co., Ltd.
Dialogue system research

2019.10 - 2019.12
Research SDE Intern @ Microsoft Development, Rinna Team
BERT-based dialogue response generator for Japanese conversations

2015.12 - 2020.9
RA @ Kyoto University, ERATO Symbiotic Human-Robot Interaction Project
Dialogue system research

Education Experience

2017.10 - 2020.9, Ph.D., Intelligence Science and Technology, Kyoto University, Japan
2015.10 - 2017.9, M.Eng., Intelligence Science and Technology, Kyoto University, Japan
2011.9 - 2015.7, B.Sc., Computer Science and Technology, Peking University, China


Publications

--- 2020 ---
Multi-referenced training for dialogue response generation
Tianyu Zhao and Tatsuya Kawahara
PDF code https://arxiv.org/abs/2009.07117 (2020)

Designing precise and robust dialogue response evaluators
Tianyu Zhao, Divesh Lala, and Tatsuya Kawahara
PDF code Short paper at ACL 2020

--- 2019 ---
Improved end-to-end speech emotion recognition using self attention mechanism and multitask learning
Yuanchao Li, Tianyu Zhao, and Tatsuya Kawahara
PDF non-official code Regular paper (oral) at Interspeech 2019

Effective incorporation of speaker information in utterance encoding in dialog
Tianyu Zhao and Tatsuya Kawahara
PDF code https://arxiv.org/abs/1907.05599 (2019)

Content word-based sentence decoding and evaluating for open-domain neural response generation
Tianyu Zhao, Shinsuke Mori, and Tatsuya Kawahara
PDF https://arxiv.org/abs/1905.13438 (2019)

Joint dialog act segmentation and recognition in human conversations using attention to dialog context
Tianyu Zhao and Tatsuya Kawahara
Link code Journal paper at Elsevier CSL 2019

--- 2018 ---
A unified neural architecture for joint dialog act segmentation and recognition in spoken dialog system
Tianyu Zhao and Tatsuya Kawahara
PDF Long paper at SIGDIAL 2018

--- 2017 ---
Joint learning of dialog act segmentation and recognition in spoken dialog using neural networks
Tianyu Zhao and Tatsuya Kawahara
PDF Long paper (oral) at IJCNLP 2017

A conversational dialogue manager for the humanoid robot ERICA
Pierrick Milhorat, Divesh Lala, Koji Inoue, Tianyu Zhao, Masanari Ishida, Katsuya Takanashi, Shizuka Nakamura, and Tatsuya Kawahara
PDF Long paper at IWSDS 2017

--- 2016 ---
Multimodal interaction with the autonomous android ERICA
Divesh Lala, Pierrick Milhorat, Koji Inoue, Tianyu Zhao, and Tatsuya Kawahara
PDF Demo paper at ICMI 2016

Talking with ERICA, an autonomous android
Koji Inoue, Pierrick Milhorat, Divesh Lala, Tianyu Zhao, and Tatsuya Kawahara
PDF Demo paper at SIGDIAL 2016

Interactional and pragmatics-related prosodic patterns in Mandarin dialog
Nigel Ward, Yuanchao Li, Tianyu Zhao, and Tatsuya Kawahara
PDF Regular paper at Speech Prosody 2016

Academic Activities

Reviewer: IJCNLP 2017, ACL 2018/2020, EMNLP 2020, COLING 2020