招待講演 Invited Talks

3rd August 2010 13:00~17:00

The 12th conference room in Souken Bldg. (14th Bldg.),
Aoyama Gakuin University (Aoyama Campus)

Access Map: http://www.aoyama.ac.jp/en/other/map_aoyama.html



"TransDec: A Data-Driven Framework for Decision-Making in Transportation System"

Prof. Cyrus Shahabi
(University of Southern California)

[Slide (PDF)]

The vast amounts of transportation datasets (traffic flow, incidents, etc.) collected by various federal and state agencies are extremely valuable in 1) real-time decision-making, planning, and management of the transportation systems, and 2) conducting research to develop new policies to enhance the efficacy of the transportation systems.  In this talk, I will present our data-driven framework, dubbed TransDec (short for Transportation Decision-Making), which enables real-time integration, visualization, querying, and analysis of dynamic and archived transportation data. I will show that considering the large size of the transportation data, variety of the data (different modalities and resolutions), and frequent changes of the data, implementation of  such a scalable system that allows for effective querying and analysis of both archived and real-time data is an intrinsically challenging data management task. Subsequently, I will focus on a route-planning problem where the weights on the road-network edges vary as a function of time due to the variability of traffic congestion.  I will show that naïve approaches to address this problem are either inaccurate or slow, motivating the need for new solutions.  Consequently, I will discuss our initial approach to this problem and demonstrate its implementation within the TransDec framework.

Cyrus Shahabi is a Professor and the Director of the Information Laboratory (InfoLAB) at the Computer Science Department and also the Director of the NSF's Integrated Media Systems Center (IMSC) at the University of Southern California. He is also the CTO and co-founder of a USC spin-off, Geosemble Technologies.  He received his B.S. in Computer Engineering from Sharif University of Technology in 1989 and then his M.S. and Ph.D. Degrees in Computer Science from the University of Southern California in May 1993 and August 1996, respectively. He authored two books and more than hundred research papers in the areas of databases, GIS and multimedia.  Dr. Shahabi has received funding from several agencies such as NSF, NASA, NIH, DARPA, AFRL, and DHS as well as several industries such as Google, Microsoft, NCR and Chevron. He is currently on the editorial board of VLDB Journal, IEEE Transactions on Parallel and Distributed Systems (TPDS), ACM Computers in Entertainment and Journal of Spatial Information Science. He is the founding chair of IEEE NetDB workshop and also the general co-chair of ACM GIS 2007, 2008 and 2009. He regularly serves on the program committee of major conferences such as VLDB, ACM SIGMOD, IEEE ICDE, ACM SIGKDD, and ACM Multimedia.  Dr. Shahabi is the recipient of NSF CAREER award as well as the U.S. Presidential Early Career Awards for Scientists and Engineers (PECASE). He is a distinguished member of ACM and a senior member of IEEE.

A Unified Graph Model for Sentence-based Opinion Retrieval

Prof. Kam-Fai Wong
(The Chinese University of Hong Kong)
[Slide (PDF)]

There is a growing research interest in opinion retrieval for on-line users’ opinions are becoming more and more popular in business, social network, etc. Practically speaking, the goal of opinion retrieval is  to retrieve documents, which entail opinions or comments, relevant to  a target specified by the user’s query. A fundamental challenge in  opinion retrieval is information representation. Existing approaches  are document-based and documents are represented by bag-of-word.  However, this representation cannot maintain the association between  topic relevance and opinion relevance due to loss of contextual  information. For this reason, existing systems fail to capture the  pairing information between an opinion and its corresponding target,  and the relationship among opinions on an identical topic is often  overlooked. This in turn seriously affects opinion retrieval  performance. In this paper, we propose a sentence-based opinion  retrieval method. We define word pairs to capture intra-sentence  contextual information. Additionally, we consider inter-sentence  information to capture the relationships among the opinions on the  same topic. Finally, two types of information are combined in a novel  unified graph-based model, which can effectively rank the documents.  Compared with existing approaches, experimental results on the COAE08  and COAE09 datasets show that our model has achieved significant  improvement.

K.F. Wong obtained his PhD from Edinburgh University, Scotland, in  1987. After his PhD, he has performed research in Heriot-Watt  University (Scotland), UniSys (Scotland) and ECRC (Germany).  At  present he is the Associate Dean (External Affairs) of the Faculty of  Engineering, a professor in the Department of Systems Engineering and  Engineering Management, and the director of the Centre for Innovation  and Technology (CINTEC), of the Chinese University of Hong Kong  (CUHK). His research interest centers on Internet programming and  applications, Chinese computing and parallel database and information  retrieval.  He has published over 200 technical papers in these areas  in various international journals and conferences and books.  He is a  fellow of HKIE and IET(UK); and a member of the ACM, CLCS, and  IEEE-CS.  He is the founding Editor-In-Chief of ACM Transactions on  Asian Language Processing (TALIP) and a member of the editorial board  of the Journal on Distributed and Parallel Databases, International  Journal on Computer Processing of Oriental Languages and International  Journal on Computational Linguistics and Chinese Language Processing.   He is the panel chair of VLDB2002, PC co-chair of IRAL03, ICCPOL01,  ICCPOL99 and IJCNLP05; General Chair of APWeb08, AIRS08, AIRS04 and  IRAL00; and also PC members of many international conferences, e.g.  some recent ones are: SIGMOD04 and DASFAA04.


Architecture-Driven Modelling Methodologies

Prof. Bernhard Thalheim
(Kiel University, Germany)
[Slide (PDF, password is required)]

Classical software development methodologies take architectural issues as granted or pre-determined. They thus neglect the impact decisions for architecture have within the development process. This omission is toleratable as long as we are considering monolithic systems. It cannot however been kept whenever we move to distributed
systems. Web information systems pay far more attention to users support and thus require sophisticated layout and playout systems. These systems go beyond what has been known for presentation systems.
 We thus discover that architecture plays a major role during systems analysis, design and development.  We thus target on building a framework that is based on early architectural decisions or on integration of new solutions into existing architectures. We aim at development of novel approaches to web information systems development that allow a co-evolution of architectures and software systems.


Thalheim Bernhard is a Professor at the Department of Computer Science
at the Christian-Albrechts University at Kiel. He received his Master's degree from Dresden University of Technology in 1975. Then he obtained his Ph.D in Discrete Mathematics from Moscow State University in 1979,
and his advanced Ph.D in Computer Science from Dresden University of Technology in 1985. In 1986, he became the Assistant Professor at Dresden University of Technology. In 1989, he became the Professor at Rostock University. In 1993, he became the Processor at Cottbus Technical University. And then since 2003 he is the Professor at Christian-Albrechts University at Kiel. His research topics are Database technology, modeling, and theory; Database management systems; Data  management; Internet technology, internet services; Intelligent information retrieval systems; Data analysis and mining systems; Information systems integration; Web information systems; Knowledge Bases; Theoretical Computer Science; Algorithmics; Discrete Mathematics;
Expert Systems; Graphical user interfaces; Decision support systems; CASE tools. He authored more than 30 edited books and he served Co-organiser of more than 30 scientific conferences, PC member of more than 230 conferences, and Steering committee chair, co-chair, member of 11 conferences. He is the recipient of Kolmogorov Professor h.c. at Lomonosov University Moscov in 2005, Peter Chen Award in 2008 and ER fellow in 2009.


Networking the Asian WordNet on WordNet Management System (WNMS)

Dr. Virach Sornlertlamvanich
(NECTEC, Thailand)

[Slide (PDF)]

WordNet has been recognized as an important language resource of lexical semantic. Each sense of word is assigned a set of synonyms called synset which plays an important role in representing the meaning of the word. Moreover, many other lexical semantic relations namely antonym, hypernym, hyponym, holonym, and meronym are provided to construct a large-scaled network of lexical semantic. The formalism of semantic representation in WordNet has a great advantage in terms of building a computation lexical database. Up to the present day, many approaches in information retrieval, query expansion, machine translation, word sense disambiguation, text classification and so on have shown the promising results in using WordNet to increase the performance. As a result, several efforts have been put to create WordNet for other languages. Asian WordNet  (AWN) is one of the approaches to build the WordNet for Asian languages by translating and networking the synsets through the defined synset ID of Princeton WordNet. To prepare an initial WordNet for a certain language, we assign the synset to a list of words from the existing bi-lingual dictionaries based on an assignment algorithm. The degree of confidence in the synset assignment has been proposed by computing the distance between a word to a member of a synset. Word synonyms are also used to serve in finding a candidate of synset. As a result, the list of candidate synsets is proposed to a word entry together with a degree of confidence score. In our approach, we show the efficiency in nominating the synset candidate by using the most common lexical information. The algorithm is evaluated against the implementation of Thai-English, Indonesian-English, and Mongolian-English bi-lingual dictionaries. The experiment also shows the effectiveness of using the same type of dictionary from different sources. The results are then reviewed collaboratively online via http://www.asianwordnet.org/.  To exhibit a cross language access to the WordNet, we use the synset in the Princeton WordNet (PWN) as a key to retrieve a set of words in the target language. Moreover, the environment for developing the WordNet for Asian languages is designed in a distributed manner on the WordNet Management System (WNMS).  Each language may take care of the environment and share its own resulted WordNet through a common API of a web service protocol.  Currently, Asian WordNet (AWN) can serve some languages depending on the progress of the percentage of translation namely, Bengali (0.90%), Hindi (7.44%), Indonesian (27.58%), Japanese (30.35%), Korean (35.93%), Lao (33.05%), Mongolian (1.38%), Burmese (16.95%), Napali (0.03%), Sinhala (0.23%), Sundanese (0.06%), Thai (55.20%), and Vietnamese (10.43%). On the WNMS, not only to browse the WordNet of each language, the implementation in cross language WordNet and multilingual dictionary can be seen by configuration on the provided web API.


Virach Sornlertlamvanich Assistant Executive Director National Electronics and Computer Technology Center (NECTEC), Thailand.
He received the doctoral degree in Computer Engineering from Tokyo Institute of Technology in 1998. He worked with NEC Corporation as a sub-project leader for Thai language processing in the Multi-lingual Machine Translation Project. He joined the National Electronics and Computer Technology Center (NECTEC) since 1992. His research interests are in the area of Natural Language Processing, Machine Translation, Information Retrieval, Knowlede Engineering and Artificial Intelligence. He was awarded by the National Research Council of Thailand as the Most Outstanding Researcher of the Year 2003 in the area of Information and Communication. He is currently the Assistant
Executive Director of National Electronics and Computer Technology Center (NECTEC). His recent efforts are on the research and development of technology for Digitized Thailand (2009) which is aimed to establish a service platform for digital content and applications
to accomplish the creative industry.

Good Papers and Good Presentations

Dr. Tetsuya Sakai
(Microsoft Research Asia)

What makes a good research paper? What if your paper gets rejected? What makes a good presentation at a conference? I will share with you my experiences as an author, a Senior Program Committee member and a Best Paper Committee member of ACM SIGIR, so that you might want to answer these questions for yourself.

Tetsuya Sakai received a Master's degree from Waseda University in 1993 and joined the Toshiba Corporate R&D Center in the same year. He received a Ph.D from Waseda University in 2000 for his work on information retrieval and filtering systems. From 2000 to 2001, he was a visiting researcher at the University of Cambridge Computer Laboratory. In 2007, he became Director of the Natural Language Processing Laboratory at NewsWatch, Inc. In 2009, he joined Microsoft Research Asia. He is Chair of IPSJ SIG-IFAT, Evaluation Co-chair of NTCIR, and Regional Representative to the ACM SIGIR Executive Committee (Asia/Pacific). He has served as a Senior PC member for ACM SIGIR, CIKM and AIRS. He is on the editorial board of Informaiton Processing and Management and that of Information Retrieval the Journal. He has received several awards in Japan, mostly from IPSJ.