Fall 2006 DB/IR Day
The Greater NY area DB/IR Day is a semi-annual conference, which brings together database and information retrieval researchers and students from academic and research institutions across the Greater New York area for an exciting technical program as well as informal discussion. The DB/IR day provides a regular forum for presenting diverse viewpoints on database systems and information retrieval, addressing current topics as well as promoting information exchange among researchers.
The Fall 2006 DB/IR Day will be hosted by New York University on Friday, October 6th, 2006. The program will consist of technical keynote lectures from distinguished researchers in databases and information retrieval. In addition, there will be a student poster session to promote awareness of current DB&IR research at various graduate departments in the North-East area, and stimulate collaborations between academia and industry.
- The talks will be at the 2nd floor of KMC, Room M2-60
- The lunch and poster session will be at the 5th floor of KMC, Room M5-50
Friday, October 6th, 2006
|10.00 - 10.30||Registration|
|10.30 - 11.00||Group Presentations|
|11.00 - 12:10||Invited Talk:
Faloutsos (Carnegie Mellon University)
|Title: Data Mining
Abstract: How can we find patterns in a sequence of sensor measurements (e.g., a sequence of temperatures, or water-pollutant measurements)? How can we compress it? How can we do forecasting and outlier detection? Sensor data analysis becomes of increasingly high importance, thanks to the decreasing cost of hardware and the increasing on-sensor processing abilities. We present some recent work on automatic monitoring of co-evolving numerical streams. The algorithms are on-line, any-time, and they only need to see the data values once. Finally, we show applications in monitoring drinking water, and in monitoring a Petabyte-class storage center, the 'self-*' system at CMU.
|12.10 - 2.00||Lunch and Poster Session|
|2.00 - 3.10||Invited Talk:
Bruce Croft (University of Massachusetts--Amherst)
|Title: Why Can't We All
Get Along? (A Historical Perspective of Structured Data
in IR Research)
Abstract: There have been many attempts to use structured data in IR applications, starting in the 1970s. These range from incorporating fields in queries to probabilistic retrieval models for XML documents. Despite this, and despite the current dominance of search engines and Web-based information from the user perspective, it is clear from looking at the proceedings of IR and database conferences that the two communities are still a long way apart, although definitely starting to test the boundaries. In this talk, I will review related research from an IR perspective in order to give some context to a discussion of current trends. Some of the specific topics I will cover include retrieval models, question answering, XML retrieval, and entity retrieval.
|3.10 - 3.45||Coffee Break|
|3.45 - 4.55||Invited Talk:
|Title: How Could We All
Get Along on the Web 2.0? (The Power of Structured Data
on the Web)
Abstract: For the longest time, the Web was used as an anonymous place where the main activity was keyword search. The Web 2.0 is changing this premise. User-centric sites such as MySpace, Flickr, and YouTube attract millions of users every day. Users supply content, organize it, and search it. Different user communities are being formed around similar interests. This constitutes a rich information source to help users find more relevant data and help advertisers target the right set of users. In this talk, I will describe the role of structured information in characterizing users' interests and in finding more relevant information on the Web. In doing so, I will borrow ideas from XML retrieval and search personalization.
|4.55 - 5.00||Poster Awards and Closing Remarks|