About me

I am Zihan (Johan) Liu (刘子涵). I am a research scientist at Nvidia Applied Deep Learning Research (ADLR) Team. I received Bachelor Degree from Zhejiang University, and Ph.D. Degree from the Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology under the supervision of Prof. Pascale Fung in Center of AI Research. I serve as the Program Committee and Reviewer at ACL, EMNLP, AAAI, NAACL, Neuips, ICML, and ACL Rolling Review. My current research interests are multilingual, few-shot learning, multimodal, and dialogue systems.

Highlights

• Retrieval-Free Knowledge-Grounded Dialogue received Best Student Paper Award from DialDoc workshop at ACL 2022.
• XPersona received Best Paper Honorable Mention Award from Conversational AI workshop at EMNLP 2021.
• Vision Guided Pre-trained Language Models got accepted at EMNLP 2021.
• Two papers accepted at NAACL 2021: Domain Adaptation for Summarization and Multimodal Emotion Recognition.
• Two papers accepted at AAAI 2021: Word Order in Cross-lingual Tasks and CrossNER.
• Cross-lingual SLU accepted at EMNLP 2020.
• Coach (Cross-domain Slot Filling) accepted at ACL 2020.
• Cross-Accented ASR accepted at Interspeech 2020.
• Two papers accepted at ACL 2020: Cross-domain Slot Filling and Code-Switched Speech Recognition.
• Low-rank Transformer got accepted at ICASSP 2020 (oral)
• Cross-lingual Task-oriented Dialogue got accepted at AAAI 2020 (oral)
• CAiRE Chatbot accepted as a demo paper at AAAI 2020.

Please feel free to contact me via email.