- April 5: Eamonn Keough Indexing and Retrieval of Time Series
http://www.ics.uci.edu/~eamonn/research/papers/dynamic-time-warping.ps
http://www.ics.uci.edu/~eamonn/research/papers/indexing time series.ps
http://www.ics.uci.edu/~eamonn/research/papers/retrieval.ps
- April 12: Cathy Blake
Beyond Market Baskets: Generalizing Association Rules
to Dependence Rules
By Craig Silverstein, Sergey Brin & Rajeev Motwani
Data Mining and Knowledge Discovery, 98
Daniel Billsus:
Andrew McCallum, Kamal Nigam, Jason Rennie, and Kristie Seymore.
Building Domain-Specific Search Engines with Machine Learning
Techniques. AAAI Spring
Symposium on Intelligent Agents in Cyberspace.
- April 19
Collaborator Discovery: tapping our hidden corporate knowledge
David Payton
HRL Laboratories, Information Sciences Lab
The world wide web has opened great new vistas of information access. While
most of us use the web daily, the act of accessing information tends to be a
very solitary experience. What if you were not alone? What if you could
easily find others who share your interests and could benefit from their
experience? Many have speculated that the next wave of evolution for the
web lies in its ability to foster a new sense of community. This talk will
show you how you can use the web to find people who share your interests.
We present a tool that helps match HRL employees based on their web browsing
activity. We discuss potential applications of this tool for corporate
knowledge capture and team building as well as potential social
ramifications.
Biography:
David Payton is a Senior Research Scientist in the Information Sciences
Laboratory. Mr. Payton received an MS in 1981 from MIT in Electrical
Engineering and Computer Science and a BS in Electrical Engineering from
UCLA in 1979. His technical interests include multi-user collaboration,
multi-agent systems, and emergent properties of complex systems.
- April 26: Igor Cadez, Hierarchical Models for Screening of Iron Deficiency Anemia,
Daniel Billsus- Agents Practice Talk.
- May 3: Dima Pavlov Prediction with local patterns using cross-emtropy
Xianping Ge
Maximum-likelihood Word Segmentation of Chinese Text
In English written text words are separated by spaces. But in written
Chinese text there are no such separators between words. Word
segmentation, the task of finding unmarked word boundaries, is useful
in many fields like information retrieval and natural language
processing. In this paper we investigate a maximum-likelihood word
segmentation algorithm for Chinese text. We propose a simple
probabilistic model that can be trained from a corpus of unsegmented
Chinese texts using the EM algorithm where no dictionary is required.
Comparing the segmentation output by the algorithm with the correct
segmentation, recall/precision of 65.65%/71.91% is achieved. If some
simple post-processing is performed, recall/precision can be boosted up
to 97.72%/91.05%. The algorithm is potentially very useful for
automatically building a dictionary from a raw corpus of unsegmented
text.
- May 10: David G. Stork, Ricoh Silicon Valley
The Open Mind Initiative
David G. Stork
Chief Scientist
Ricoh Silicon Valley
Consulting Associate Professor of Electrical Engineering
Stanford University
stork@rsv.ricoh.com
www.Open-Mind.org
We propose the Open Mind Initiative, to provide a framework
for large-scale collaborative efforts in building components of
"intelligent" systems that address common-sense reasoning,
document and language understanding, speech and character
recognition, and so on. Based on the Open Source methodology, the
Open Mind Intitiative allows domain specialists to contribute
algorithms, tool developers to provide software infrastructure and
tools, and non-specialists to contribute information to large
knowledge databases. An important challenge is to make it easy
and rewarding for non-specialists to provide information. We
review free software and open source approaches, including their
business and economic issues models, and past software projects of
particular relevance to Open Mind. We then describe some of the
technical details associated with Open Mind projects, such
as insuring data integrity and learning from heterogeneous
contributors and conclude with general challenges and
opportunities.[1,2]
[1] "Character and Document Research in the Open Mind Initiative"
by David G. Stork, International Conference on Document Analysis
and Recognition (ICDAR99), 1999, in press.
[2] "The Open Mind Initiative" by David G. Stork, Communications
of the ACM (submitted) 1999.>
- May 17: Stephen Bay: Contrast Sets
- May 24: MARS
- May 31: Memorial Day Holiday.
- June 7: Scott Gaffney; Kalev Kask