Ng, Jun Ping

Ng, Jun Ping

ngjp*ad*nus(dot)edu(dot)sg

AS6-04-13
COM1, 13 Computing Drive
National University of Singapore
Singapore 117417

+65 6516 1371

 

© All Rights Reserved 2010

I am currently a PhD student at the School of Computing, National University of Singapore. My research interests lie predominantly in improving natural language applications such as question-answering and summarization through the use of semantic approaches.

My thesis advisor is A/P Kan Min Yen, who heads the Web Information Retrieval / Natural Language Processing Group (WING).

A summary of my academic work is presented in this web page. Please feel free to send me any comments and feedback, or to get in touch with me regarding the work I have been doing.

I am very drawn to natural language processing (NLP) and its applications. I am interested in improving the way we access data, and have worked on applications such as question-answering (QA) and multiple document summarization. Currently I am exploring ways to fuse diverse information resources together, and to present this information to end-users in a more coherent, useful way.

As part of my research, I have developed an open-source QA system -- QANUS. QANUS is developed to serve as a framework to support rapid prototyping of QA systems, and in time to come serve as a verifiable, reproducible benchmark for QA systems.

I have also developed with my colleagues a state-of-the-art multiple document summarization system (SWING). SWING [pdf] [Github] participated in the summarization track of the Text Analysis Conference (TAC) 2011 and was the best performing system measured with the automatic ROUGE metric.

Reviewed Publications

Extracting Formulaic and Free Text Clinical Research Articles Metadata using Conditional Random Fields
Sein Lin, Jun-Ping Ng, Shreyasee Pradhan, Jatin Shah, Ricardo Pietrobon, Min-Yen Kan
Proceedings of the NAACL HLT 2010 Second Louhi Workshop on Text and Data Mining of Health Documents
2010, Los Angeles, pp 90-95

Dynamic Markov Compression Using a Crossbar-like Tree Initial Structure for Chinese Texts
Ghim-Hwee Ong, Jun-Ping Ng
Proceedings of the International Conference on Information Technology and Applications
2005, Sydney, pp 407-410

Exploring the Initial Structures of Dynamic Markov Modeling for Chinese Text Compression
Ghim-Hwee Ong, Jun-Ping Ng
Proceedings of the International Symposium on Distributed Computing and Applications to Business, Engineering and Sciences
2004, Wuhan, pp 460-463

 

Non-refereed Publications

SWING: Exploiting Category Specific Information for Guided Summarization
Jun-Ping Ng, Praveen Bysani, Ziheng Lin, Min-Yen Kan and Chew-Lim Tan
Proceedings of the Text Analysis Conference (TAC)
2011, Maryland

 

Academic Reports

QANUS: An Open-source Question-Answering Platform
Jun-Ping NG and Min-Yen KAN
2010

Processing Sentiments and Opinions in Text
Jun-Ping NG
Survey paper done as part of course work
2009

Enhancing Honeypot Stealthiness
Jun-Ping NG
Masters's Thesis
2006

Dynamic Markov Modeling and Compression for Chinese Textual Data
Jun-Ping NG
Honours Year Project Report
2005

 

And this points to my very modest listing on DBLP.

There are many things I like about teaching, such as the interaction with the students, as well as the chance to share with them what I have learnt. I try to put aside the time thus to take on teaching opportunities every semester. Some of the courses I have helped to teach are listed below.


National University of Singapore
AY10/11 Sem 1 CS3243 Artificial Intelligence
AY09/10 Sem 2 CS3235 Introduction to Computer Security
AY09/10 Sem 1 CS2106 Operating Systems
AY08/09 Sem 2 CS2100 Computer Organisation
   
Nanyang Polytechnic
AY11/12 Sem 1 IT2524 Operating Systems
AY10/11 Sem 1
 
  		IT3110 InfoSecurity Technology
IT3506 InfoSecurity Technology
IT2524 Operating Systems
AY09/10 Sem 2
  		IT1534 Cryptography and Applications
IT3110 InfoSecurity Technology
AY09/10 Sem 1 IT3110 InfoSecurity Technology
AY08/09 Sem 2 IT2126 OOP Using Java

This is where I place links to some misc pages I have.

And for lack of a better place to house these links, I have these here for now. They represent a collection of articles/media that I have come across and which I find to be provoking and possibly inspiring.