Avatar

Liangming Pan

Ph.D. Student

National University of Singapore

Biography

Liangming Pan (潘亮铭) is a third year Computer Science Ph.D. student at National University of Singapore, jointly advised by Prof. Min-Yen Kan and Prof. Tat-Seng Chua. Prior to joining NUS, he received a Master degree from School of Computer Science at Tsinghua University in June, 2017, working with Prof. Juanzi Li and Prof. Jie Tang. He obtained the Bachelor degree in Beihang University (2010 - 2014).

His board research interests include knowledge base, natural language processing, and data mining. To be specific, his research topics include neural question generation, text style transfer, and zero/few-shot image recognition.

Interests

  • Text Generation
  • Knowledge Graph
  • Multi-media Learning

Education

  • PhD in Computer Science, 2018

    National University of Singapore

  • MEng in Computer Science, 2014

    Tsinghua University

  • BSc in Software Engineering, 2010

    Beihang University

News

Two paper accepted by ACL 2020!

Two of our papers, “Semantic Graphs for Generating Deep Questions” and “Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymenwas”, were accepted by ACL 2020. The paper and code link will soon be released.

One paper accepted by CVPR 2020!

Our paper “Hyperbolic Visual Embedding Learning for Zero-Shot Recognition” was accepted by CVPR 2020 (acceptance rate: 22%). [paper link]

Paper list on neural question generation on Github.

We created a paper list on Github to summarize the recent research on neural question generation. [Github link]

One paper accepted by AAAI 2020!

Our paper “Zero-shot Ingredient Recognition by Multi-Relational Graph Convolutional Network” was accepted by AAAI 2020 (acceptance rate: 20.6%). [paper link]

Survey paper on neural question generation

We have written a survey paper on recent advances in neural question generation, and posted it on ArXiv. [paper link]

Projects

Question Generation Paper List Star

A paper list that summarizes the recent papers on neural question generation.