Stephen Wan
Research Projects Officer ICT
Contact
Cnr Vimiera and Pembroke Roads
Marsfield NSW 2122
Tel: 61 2 93724703
Stephen.Wan@csiro.au
Science Area
- Human Information Interaction
Biography
My role in the Information Delivery group is to research and implement applications demonstrating advances in Natural Language Processing (aka Computational Linguistics). Specifically, my research is focused on finding those actionable nuggets of information (documents, paragraphs, sentences, facts, keywords) within a document that helps a user perform his or her task. As such, I am interested in Automatic Text Summarization and Information Extraction, and their use in delivering contextualised information for the user, taking into account the user's interests, tasks and information query needs. Currently, we have been developing expertise in providing such information-based services in Enterprise domains. I generally use tools and methods developed in the related fields of Information Retrieval, Statistical Text Generation (specifically, statistical syntax models and language modelling), and Supervised and Unsupervised Machine Learning in order to build such applications.
I am also interested in the following application spaces: Government 2.0; Creative uses of NLP; Digital Libraries; NLP for the Web; Social Media technologies
I am also currently completing a PhD in the area of Automatic Text Summarisation.
I also explored the use of summarisation techniques in the Email domain (This work was conducted while visiting Columbia University to work on Email Thread Summarization.)
At CSIRO, I worked on the following projects (see links below for project pages):
CARRS: Computer Automated Road Report System
TIDDLER: Tailored Information Delivery
IBES: A summarisation extension for Firefox
CSIBS: The Citation-Sensitive In-Browser Summariser
Academic Qualifications
| 2001 | Bachelor of Science(Honours -- First Class), Macquarie University |
| 1999 | Bachelor of Science, Adelaide University |
| 1999 | Bachelor of Arts, Adelaide University |
Recent Professional Experience
| 2006-Present | Research Engineer, CSIRO |
| 2005-2006 | Editorial Assistant, Journal of Computational Linguistics |
| 2004 | Academic Tutor, Macquarie University |
| 2003 | Visiting Research, Columbia University |
| 2000-2002 | Research Engineer |
| 1999 | Computer Science Practical Supervisor, Macquarie University |
| 1998-1999 | Summer Vacation Scholar, CSIRO |
| 1998 | Computer Science Practical Supervisor, Adelaide University |
| 1997 | Summer Vacation Researcher, Microsoft Research Institute, Macquarie University |
Achievements & Awards
| 2009 | Finalist Elsevier Grand Challenge |
| 2008 | Semi-Finalist Elsevier Grand Challenge |
| 2006 | Outstanding Reviewer Certificate, COLING/ACL 2006 |
| 2006 | Award for Best Student Presentation, Australasian Language Technology Workshop 2006 |
| 2002-2005 | CSIRO Mathematical and Information Sciences Top-Up Scholarship |
| 2002-2005 | Research Award for Areas of Centres of Excellence, Macquarie University |
Other Highlights
| 2009 | Selected for the CSIRO Talent Management Program |
Summary of Science & Technical Output
| Books/Book chapters | 0 |
|---|---|
| Journal | 2 |
| Refereed Conference/Workshop | 27 |
| Technical/Client Reports | 2 |
| Invited Presentations | 0 |
| Patents | 0 |
Student Supervision
| 2009 | Julien Blondeau |
| 2009 | Michael Muthukrishna |
| 2009 | James McHugh |
| 2008 | Julien Blondeau |
Science Citizenship
| 2009 | ACM Computing Survey reviewer |
| 2009 | Program Committee for UCNLG 2009 |
| 2009 | Program Committee for SIGIR 2009 |
| 2009 | Program Committee for ADCS 2009 |
| 2009 | Program Committee for ACL-IJCNLP 2009 |
| 2008 | Program Committee for COLING 2008 |
| 2008 | Program Committee for EMNLP 2008 |
| 2008 | Program Committee for ALTA 2008 |
| 2007 | Program Committee for ACL'07 Student Research Workshop |
| 2006 | Program Committee for ACL'06 Student Research Workshop |
| 2005 | Co-Chair ACL'05 Student Research Workshop |
| 2005 | SIGGEN Mailing List Maintainer |
| 2005 | Reviewer for Journal of Computational Linguistics |
| 2004 | Student member on the board for the Australasian Language Technology Association (ALTA) |
| 2004 | Student member on the board for the Special Interest Group on Text Generation (SIGGEN) |
| 2004 | Program Committee for ACL SRW '04 |
| 2003 | Organiser of the Language Technology Seminar and SALS-SIG Series |
| 2000-2001 | Co-organiser of the HAIL seminars |
| 2000 | Maintained the OZCHI 2000 conference website. |
Top 10 Publications
| Publication details |
|---|
| Stephen Wan, Cecile Paris, and Robert Dale (2009) "Supporting Browsing-Specific Information Needs: Introducing the Citation-Sensitive In-Browser Summariser". To Appear in the Journal of Web Semantics. |
| Stephen Wan, Mark Dras, Robert Dale and Cécile Paris (2009) Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument Satisfaction Model. In the Proceedings of Conference of the European Chapter of the Association for Computational Linguistics(EACL 2009). Athens, Greece. |
| Stephen Wan, Robert Dale, Mark Dras and Cecile Paris (2008) Seed and Grow: Augmenting Statistically Generated Summary Sentences using Schematic Word Patterns. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2008), 543-552. Hawaii, USA. |
| Andrew Mutton, Mark Dras, Stephen Wan and Robert Dale (2007) GLEU: Automatic Evaluation of Sentence-Level Fluency. In the Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics. Prague, Czech Republic |
| Stephen Wan, Mark Dras, Robert Dale and Cecile Paris (2006) Using Dependency-based Features to Take the "Para-farce" out of Paraphrase. Proceedings of the Australasian Language Technology Workshop 2006 (ALTW 2006), 131-138. Sydney, Australia |
| Stephen Wan, Mark Dras, Robert Dale and Cécile Paris (2005) Towards statistical paraphrase generation: preliminary evaluations of grammaticality. In the Proceedings of The 3rd International Workshop on Paraphrasing (IWP2005) at IJCNLP 2005. Jeju Island, South Korea |
| Stephen Wan and Kathleen McKeown. (2004) Generating Overview Summaries of Ongoing Email Thread Discussions. In Proceedings of COLING 2004, the20th International Conference on Computational Linguistics. Geneva, Switzerland |
| Cécile Paris, Stephen Wan, Ross Wilkinson and Mingfang Wu. (2001). Generating Personal Travel Guides – and who wants them? In Proceedings of the International Conference on User Modelling (UM2001); Sonthofen, Germany, July 13-18, 2001 |
| Ross Wilkinson, ShiJian Lu, Francois Paradis, Cécile Paris, Stephen Wan, and Mingfang Wu. (2000) Generating Personal Travel Guides from Discourse Plans. In Proceedings of International Conference on Adaptive Hypermedia and Adaptive Web-based Systems. Trento, Italy, August, 2000 |
| Wan, Stephen and Verspoor, Cornelia Maria. (1998). Automatic English-Chinese name transliteration for development of multilingual resources. In Proceedings of COLING-ACL'98, the joint meeting of 17th International Conference on Computational Linguistics and the 36th Annual Meeting of the Association for Computational Linguistics, Montreal, Canada |