-
An
Overview of Temporal Information Extraction, Prof Kam-Fai
Wong, The Chinese University of Hong Kong, Hong Kong
- Abstract
Research of temporal
Information Extraction originated in 1990’s as a subtask of
named
entity recognition. To date, scope of this research is extended
ranging from temporal expression
extraction and annotation to temporal reasoning and understanding.
This research currently
becomes an independent hot topic and greatly benefits NLP tasks
such as question answering,
information extraction, and text summarization. In this article
we target at a brief presentation of
most aspects of this research followed by an analysis of challenges
encountered together with
solutions currently employed. An investigation of future directions
of this research is provided in this
article.
- Bibliography
of Prof Wong
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 a professor in the Department of Systems Engineering
and Engineering Management, the Chinese University of Hong Kong
(CUHK) and in parallel serves as the director of the Centre for
Innovation and Technology (CINTEC), CUHK. His research interest
focuses on Chinese computing and parallel database and information
retrieval. He has published over 130 technical papers in these areas
in various international journals and conferences and books. He
is a member of the ACM, CLCS, IEEE-CS AND IEE (UK). He is the founding
Editor-In-Chief of ACM Transactions on Asian Language Processing
(TALIP), co-Editor-in-Chief of International Journal on Computer
Processing of Oriental Languages and a member of the editorial boards
of the Journal on Distributed and Parallel Databases and International
Journal on Computational Linguistics and Chinese Language Processing.
He is the panel chair of VLDB2002, PC co-chair of ICCPOL01, ICCPOL99,
IJCNLP05, and General Chair of AIRS04 and IPAL00, and also PC members
of many international conferences, some recent ones being: WISE02,
ICWL02, COLING02, IRAL03, ICCPOLO3 and SIGMOO04.
[TOP]
- Advanced
Techologies for Information Access, Dr Tetsuya
Sakai, Toshiba Laboratory, Kawasaki, Japan
- Abstract
This paper briefly describes Toshiba Knowledge Media Laboratory's
recent research efforts for effective information retrieval and
access. Firstly, I will mention the main research topics that are
being tackled by our information access group, including document
retrieval, speech-input/multimedia question answering, and evaluation
metrics. Secondly, I will focus on the problem of cross-language
information retrieval and access, and describe a system called BRIDJE
(Bi-directional Retriever/Information Distiller for Japanese and
English), which achieved many gold-medal performances at the recent
NTCIR (a.k.a. "Asian TREC") workshop. Finally, I will
conclude the paper by mentioning some unsolved problems and suggesting
possible directions for future Information Access research.
- Bibliography
of Dr
Sakai
Tetsuya Sakai received a Master's degree in Engineering from Waseda
University in 1993 and joined 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 University of CambridgeComputer
Laboratory, under the supervision of Professor Karen Sparck Jones
and Professor Steve Robertson. He is currently a Research Scientist
at Toshiba Corporate R&D Center Knowledge Media Laboratory.
[TOP]
- Translation
Probabilities in Cross-Language Information Retrieval,
Prof Jong-Hyeok Lee, Pohang
University of Science and Technology, Korea
- Abstract
Translation ambiguity is one of the major problems in dictionary-based
cross-language information retrieval. To attack the problem, indirect
methods, which do not explicitly resolve translation ambiguity,
rely on query-structuring techniques such as Pirkola's method and
balanced translation. Direct methods try to assign translation probabilities
to translations, normally by employing co-occurrence of translations
in target documents as disambiguation clues. So far, translation
probabilities in direct methods have been mainly used to select
top N translations that are equally correctly considered in query
formulation. However, translation probabilities themselves may influence
term importance, resulting in affecting retrieval effectiveness.
In order to study the effect of translation probabilities on retrieval
effectiveness in direct methods, this paper empirically investigates
the following issues: factors affecting translation probabilities,
translation probabilities vs. term weights, the accuracy of translation
disambiguation vs. retrieval effectiveness, top N translations vs.
retrieval effectiveness.
- Bibliography
of Prof Lee
Jong-Hyeok Lee received his B.S. degree in mathematics education
from Seoul National University in 1980, and then his M.S. and Ph.D.
degrees in Computer Science from KAIST (Korea Advanced Institute
of Science and Technology), in 1982 and 1988, respectively. From
Nov. 1989 through Jan. 1991, he worked as a visiting researcher
for NEC C&C institute, Japan. After then he joined and has been
with POSTECH (Pohang University of Science and Technology) as an
assistant and associate professor till Mar. 2003, and then as a
professor. During the year from Aug. 1998 he worked as a visiting
scholar for CRL/NMSU, USA. His research interests include machine
translation, information retrieval, and multi-lingual language processing.
[TOP]
- Text
Summarization with Rhetorical Information, Prof Sung
Hyon Myaeng, Information and Comunications University, Korea
- Abstract
We describe a text summarization method that employs a hierarchical
clustering algorithm and rhetorical structure information. A summary
consists of key sentences representing the core content of a document,
which are selected based on the result of sentence clustering. Since
individual sentences are often too short for similarity calculations
in clustering, they are combined based on the rhetorical structure
information in the document. Instead of relying on full parsing,
we only use the rhetorical structure information immediately recognizable
at the surface level, as a way to make this approach practical and
usable across different languages.
- Bibliography
of Prof Myaeng
Dr. Sung Hyon Myaeng is currently a professor at Information and
Communications University (ICU), Korea. Prior to this appointment,
he was a faculty at Chungnam National University, Korea, and Syracuse
University, USA. His research work has been in cross-language IR,
summarization, topic detection & tracking, categorization, distributed
IR and digital libraries. He was a program committee chair for ACM
SIGIR, 2002, and for AIRS, 2004.
[TOP]
- Automatic
Identification of Oriental and Other Scripts in Image Documents,
Prof Ching Y. Suen, Concordia
University, Canada
- Abstract
Large quantities of paper documents are still produced or received
by many organizations. Nowadays they are being handled electronically
through imaging and digital means such that the resulting document
images can be processed by OCR for information retrieval and data
mining. Since OCR is language dependent, the language of the original
document must be identified first by advanced technology. This paper
describes two methods of identifying Oriental languages among four
language groups, i.e. Oriental, Roman, Cyrillic, and Arabic. One
method is based on features extracted from the shapes of words and
letters, while the other one is based on global analysis of text
pieces using Gabor filters. Experimental results on hundreds of
documents indicate that both automatic classification approaches
look quite promising. The use of linguistic analysis to enhance
the results is also discussed.
-
Bibliography
of Prof Suen
Ching Y. Suen received an M.Sc.(Eng.) degree from the University
of Hong Kong and a Ph.D. degree from the University of British Columbia,
Canada. In 1972, he joined the Department of Computer Science of
Concordia University where he became Professor in 1979 and served
as Chairman from 1980 to 1984, and as Associate Dean for Research
of the Faculty of Engineering and Computer Science from 1993 to
1997. He has guided/hosted 65 visiting scientists and professors,
and supervised 60 doctoral and master's graduates. Currently he
holds the distinguished Concordia Research Chair in Artificial Intelligence
and Pattern Recognition, and is the Director of CENPARMI, the Centre
for PR & MI.
Prof. Suen is the author/editor of 11 books and more than 400 papers
on subjects ranging from computer vision and handwriting recognition,
to expert systems and computational linguistics. He is the founder
of "The International Journal of Computer Processing of Oriental
Languages" and served as its first Editor-in-Chief for 10 years.
Presently he is an Associate Editor of several journals related
to pattern recognition.
A Fellow of the IEEE, IAPR, and the Academy of Sciences of the Royal
Society of Canada, he has served several professional societies
as President, Vice-President, or Governor. He is also the founder
and chair of several conference series including ICDAR, IWFHR, and
VI. He was the General Chair of numerous international conferences,
including the International Conference on Computer Processing of
Chinese and Oriental Languages in August 1988 held in Toronto, International
Conference on Document Analysis and Recognition held in Montreal
in August 1995, and the International Conference on Pattern Recognition
held in Quebec City in August 2002.
Dr. Suen has given 150 seminars
at major computer industries and various government and academic
institutions. He has been the principal investigator of 25 industrial/government
research contracts, and is the recipient of prestigious awards,
including the ITAC/NSERC Award from the Information Technology Association
of Canada and the Natural Sciences and Engineering Research Council
of Canada in 1992 and the Concordia "Research Fellow"
award in 1998.
[TOP]
-
Sentiment
and Content Analysis of Chinese News Coverage,
by Prof Benjamin T'sou,
City University of Hong Kong, Hong Kong
- Abstract
This paper explores
the salient differences between spread of the polar items in terms
of paragraphs and sentences and the problem of multiple foci within
coherent textual segments. Our findings indicate that paragraph
spread is comparable to sentence spread and that the problem of
multiple foci is far-reaching and deserves considerable further
attention. This is especially so for political figures in an election
when comparison between the challenger and the incumbent is much
more common than coverage or analysis of only the incumbent.
- Bibliography
of Prof T'sou
Professor Benjamin T'sou is chair professor of Linguistics and Asian Languages,
director of Language Information Sciences Research Centre at City University of Hong Kong.
[TOP]
|