Date and time: 19th April 2010, 1:00 PM
Location: 219 SEO
Committee: Prof. Barbara Di Eugenio, Prof. Peter Nelson, Prof. Bing Liu,
Dr. Susan McRoy (University Of Wisconsin, Madison), Dr. Swee Mok (Motorola
Research Lab, Schaumburg, IL)

Abstract:

With the drastic increase in the personal music collections of individuals and the increased availability of data on the internet, recommendation systems are becoming increasingly popular. Many users decide whether or not to try a product by looking at reviews. However, there are far too many reviews for each product and it is a tedious task to read all of them. The main focus of this research is to produce a coherent and grammatical summary of reviews of individual songs. As reviews of songs are rarely available, this information has to be extracted from album reviews, which encompass several songs from the same album.

A music recommendation system has been developed. A formative study was carried out to determine that users are interested to read reviews in the recommendation system. An automatic summarization framework was proposed and developed, that combines extraction of information about songs from album reviews and generation techniques to produce summaries of reviews of individual songs. Fine-grained song feature summaries were incorporated into a music recommendation system, SongRecommend. Evaluation of SongRecommend with 39 users showed that users were able to make quicker decisions when presented with the summary as compared to the full album review; additionally, their decisions appeared to be more informed as their choices of recommendations to follow were more varied than in the control condition.

Barbara Di Eugenio is co-PI on a new NSF award (PI: Milos Zefran, co-PI: Jezekiel Ben-Arie) that aims at developing assistive robots for the elderly. The team will focus on the technological challenge of creating an effective interface that can seamlessly integrate speech, gestures and haptic signals (force exchange). These different modalities co-constrain the interpretation of what the user is communicating to the robot. This project aims at robots that can assist elderly people in performing mundane, daily activities, from the more basic (getting out of bed), to the more complex (cooking). Such robots would help the elderly stay in their homes longer, with great benefits to the elderly people themselves, their caregivers, and society at large. This award is a collaboration between ECE and CS at UIC, and Mark Foreman, a UIC professor emeritus who is now with the Department of Gerontological Nursing at Rush University.

The UIC Press Release can be found here.

The Chicago Tribune news can be found here

Davide Fossati, Computer Science PhD student, received the prestigious "50 for the Future" award from the Illinois Technology Foundation. This award is designed to recognize and honor the most promising technology students in Illinois.
http://50forthefuture.org

Davide is currently working in the Natural Language Processing Lab, directed by professor Barbara Di Eugenio. His research focuses on Intelligent Tutoring Systems, which are computer systems that can interact with students and help them learn. His latest project, iList, is a system that helps college students practice and learn linked lists, a fundamental topic in Computer Science curricula. The system has been already used in several classrooms at UIC and the US Naval Academy.
http://www.fossati.us

The Illinois Technology Foundation’s mission is to support the development of a technology talent pipeline that begins in elementary school, is refined in high school, and is fully developed in our region’s higher education graduates. The Foundation facilitates relationships and efforts across industry, academia, students, and government, developing and managing targeted programs within the talent pipeline. Through action, leadership, and collaboration, the Foundation supports and nurtures the technology talent to ensure a viable and a regional wealth creating economy. The Foundation is the philanthropy arm of the Illinois Technology Association (ITA), a membership organization of more than 500 Illinois technology companies who support the development of a stronger technology talent pipeline in the region.
http://www.illinoistechfoundation.org

The NLP laboratory(Dr. Barbara Di Eugenio, director) has obtained new funding from the "Motorola University Partnership in Research" program for "Intelligent Aggregation for Mobile Search." The project focuses on developing resources and algorithms to perform aggregation, i.e., summarization of long lists of concepts. The problem is important for effective mobile search, since long lists can overwhelm small displays, are difficult to remember when spoken, and are difficult to navigate on a small device. The problem is challenging, since it touches on unsolved research issues. First, we will need to develop new algorithms to generate meaningful groupings of the items that appear on long lists; in many cases, such as aggregating email messages, the possible dimensions are too numerous to define a priori and must be dynamically determined. Second, mobile search cannot be conceived of as a sequence of isolated queries: a user will follow up to an answer from the mobile search engine with further requests. Hence, the system must be able to address new requests from the user that will refer to the entities dynamically created by the system.

Xin Lu will be defending her thesis this thursday. Details about her defense are outlined below:

Location: SEO 1000
Time: 2:00 pm, Thursday, June 21, 2007.
Speaker: Xin Lu
Advisor: Barbara Di Eugenio
Committee: Barbara Di Eugenio, Bing Liu, Tom Moher, Stellan Ohlsson, Martha
Evens (IIT)

Abstract:

Intelligent tutoring systems can provide benefits of one-on-one instruction automatically and cost effectively. To make the intelligent tutoring systems as effective as expert human tutors, this research aims at investigating what type of natural language feedback an intelligent tutoring system should provide and how to implement the feedback generation to engender significantly more learning than unsupervised practice. This research demonstrates the utility of a computational model of expert tutoring in generating effective natural language feedback in intelligent tutoring systems.

This presentation will start from a comprehensive study of the difference between one expert tutor and two non-expert tutors in effectiveness, behavior and language. Then it will present a rule-based model of expert tutoring which takes advantage of a machine learning technique, Classification based on Associations. The tutorial rules are automatically learned from a set of annotated tutorial dialogues, to model how the expert tutor makes decisions on tutors attitude, domain concepts and problem
scopes to focus on, and tutor moves. This presentation will also describe a framework of feedback generation with 3-tier probabilistic planning to employ the model of expert tutoring in the natural language feedback generation for intelligent tutoring systems. The 3-tier planning automatically generates, selects and monitors plans for generating
effective tutorial feedback based on the rule-based model and the information state which keeps track of the interaction in the intelligent tutoring system. At last, an evaluation of the framework will be discussed.