News

• 1 paper accepted by ICLR 2024 as poster presentation.  We make the first step towards scaling up syntactic language models.  For details. please refer to ReCAT

• 1 paper acceepted by EMNLP 2023 Findings. We model-specific prompt optimization in order to find an ``optimal'' prompt out of an intent for a specific LLM. For details, please refer to MAPO

About Me

I have joined Meituan-Dianping Group as the head of NLP team.  My previous roles include  principal applied scientist lead in Microsoft Xiaoice Team and  lead researcher in Microsoft Research Asia (MSRA).  I joined MSRA in 2012 and had been a member of Natural Language Computing (NLC) group until December 2017. Before I became an employee in MSRA, I was a joint student of MSRA and Peking University. My advisor is Professor Hang Li.

I obtained a B.S. in Applied Mathematics from Peking University in 2007 and earned my Ph.D. in Applied Mathematics from Peking University in 2012.

My research interests include machine learning, natural language processing, and information retrieval.

For years, I dedicate myself to research of conversational AI.  My work includes single-turn conversation, multi-turn conversation, and knowledge-grounded conversation.  I am a key technology contributor to core chat engines of Microsoft XiaoIce (微软小冰) v2, v3, v4, v5 and v6 and Microsoft Rinna (りんな). My significant achievements include the launching of generation based chat engines in  XiaoIce and Rinna and Empathy Model in Rinna. Particularly, my work serves Microsoft's chatbot in Indonesia with full dialogue generation technologies. The chatbot now has more than 1.5 million users on LINE Indonesia.