I am a first year PhD student at NUS Graduate School for Integrative Sciences and Engineering (NGS), National University of Singapore. I am associated with the Web Information Retrieval / Natural Language Processing Group (WING) and jointly advised by Prof. Min-Yen Kan and Prof. Tat-Seng Chua. My board research interests include knowledge base, natural language processing, and data mining. My thesis topic is on learning to generate complex questions from both texts and knowledge bases. Besides this, I am also working on topics related to expertise style transfer, and zero/few-shot image recognition.

Prior to joining NUS, I received my Master degree from Tsinghua University under the guidance of Prof. Juanzi Li and Prof. Jie Tang (2014 - 2017). My master’s thesis is about data mining in Massive Open Online Courses (MOOCs). Before that, I obtained my bachelor degree in Beihang University (2010 - 2014).

News

• [Nov 11, 2019] One paper is accepted by AAAI 2020 about Zero-shot Food Ingredients Recognition!

• [May 22, 2019] A survey paper on Neural Question Generation (NQG) is posted in the arXiv.

Research Topics

• Data Mining in MOOCs

  Recent years, MOOCs have become increasingly popular and offered students around the world the opportunity to take online courses from different universities. The large and growing amounts of online education data present both open challenges and significant opportunities for data mining research to enrich educational offerings. From the year 2016 to 2017, I have been working on how to efficiently discover the knowledge concepts in MOOCs and also discover the relationships between these concepts.

• Cross-lingual Knowledge Graph

  The global knowledge sharing makes large-scale multi-lingual knowledge bases an extremely valuable resource in the Big Data era. In the year 2015, my research mainly focus on cross-lingual knowledge graph construction, and I also research on cross-lingual knowledge linking, which aims to discover and link equivalent entities between multi-lingual knowledge bases.