Projects

ILS is currently conducting research on several federally funded projects, including:

Current Projects

ARCSS : Advanced Research in Computational Social Science

This effort aims to assist the U.S. Army Research Laboratory (ARL) in developing a world-class computational social science lab complementing its effort in network science and related disciplines as part of the ARL Open Campus initiative. This project aims to significantly advance the state-of-the-art in the emerging field of computational social science. Specifically, the goal is to develop and validate novel methodology for studying language and human behavior using computational methods that are firmly grounded in social science theory.

Project Manager and PI:
Professor Tomek Strzalkowski
Key Personnel:
Ms. Samira Shaikh

 

REMND : Robust Extraction of Metaphors from Novel Data

project REMND

The REMND project (Robust Extraction of Metaphors in Novel Data) is developing and validating an automated system for recognizing and understanding metaphors in cross-cultural communication. Our objective is to identify and analyze metaphors in naturally occurring text and apply the resulting capability in practical, analytic case studies. The end result of the successful REMND project will include vastly advanced automated language processing capabilities suitable for applications in cross-cultural contexts.Project manager and PI:
Professor Tomek Strzalkowski
Key Personnel:
Dr. Sarah Taylor
Professor Aaron Broadwell
Professor Laurie Feldman
Ms. Kirby Plessas

 

CYCLES : Cycles of Your Cognitive Learning, Expectations, and Schema

project CYCLES

An ILS research team is developing a computer game to train people to recognize cognitive biases they routinely use when confronted with incomplete information or operating under time pressure. Such biases can lead to bad decisions in critical matters, including national security. “This project will advance educational game research by systematically and experimentally identifying a serious game design that leads to most effective learning,” explained Strzalkowski, who is also director of the University’s Institute for Informatics, Logics and Security Studies, where the research will be conducted. “Our objective is to turn computer games, which people generally view as entertainment, into powerful learning tools.” In partnership with the local game company 1st Playable Productions, the CYCLES project will develop a computer game that will teach players how to recognize six common cognitive decision-making biases: confirmation bias, fundamental attribution bias, bias blind spot, representativeness bias, anchoring bias and projection bias. The goal is to reduce players dependency on bias in real decision-making situations by as much as 65 percent.Project manager and PI: Professor Tomek Strzalkowski
co-PI: Professor Jennifer Stromer-Galley

 

CUBISM

The goal of the CUBISM project is to develop and implement an algorithm for the deep and robust analysis and understanding of multi-party conversations — including conversations that are only partially and inaccurately transcribed, and likely to contain obscure and even deceptive language. We will accomplish this by developing a novel algorithm to systematically expose pragmatic knowledge in the conversation that is otherwise contextually bound and only implicitly expressed. In particular, the proposed algorithm will make explicit the conversation’s dynamics (e.g., critical topic shifts and other sociolinguistic features of dialogue) through which the interlocutors’ beliefs and intentions as well as those of third parties can be modeled and projected. The algorithm is applicable to both English and foreign language conversations (e.g., Chinese, Farsi), including multi-party (more than two participants) conversations and one-sided conversations — two-party conversations where one party’s utterances are unavailable.Project manager and PI: Professor Tomek Strzalkowski

 

Completed Projects

DSARMD : Detecting Social Actions and Roles in Multiparty Dialogue

project DSARMD

The objective of this project is to develop automated methods for modeling and recognizing participants’ social actions and social roles in small groups based on the linguistic evidence in their interactions. These methods will be based on detecting a wide range of linguistic features (lexical, syntactic, discourse, etc.) so that they can apply effectively to different communication media and, with appropriate modifications, to different languages. When fully functional, the DSARMD system will provide an efficient and effective means for understanding the social dynamics of small groups across languages and cultures, as well as computer-mediated communication.Project manager and PI: Professor Tomek Strzalkowski
co-PI: Professor Jennifer Stromer-Galley
co-PI: Professor Aaron Broadwell
co-PI: Dr. Sarah Taylor

 

SCRIBE : Social & Cultural Research in Bounded Environments
The objective of this research is to investigate a combination of Virtual World (VW) dimensions (avatars and their representations, communication, and behavior, as seen through the lens of group dynamics) to infer or predict at least six Real World (RW) characteristics. Our primary focus will be on four characteristics: gender, age, “digital nativity” (online experience), and degree of influence (leadership style). A secondary focus will include two additional characteristics: educational level and worldview (conformity). Moreover, data collection and model development will accommodate the capability to analyze additional RW characteristics, including culture, regional location, native language, and psychological factors. This approach will permit multi-level analyses and create a dataset useful to future research.Albany co-PI’s: Prof. Tomek Strzalkowski and Prof. Jennifer Stromer-Galley
A joint project with Lockheed Martin Corporation, Colorado State University and Ohio University

 

COLLANE : The Collaborative Analytical Environment

project COLLANE

This project aims at developing advanced information access and analysis tools that exploit the strength of collaborative analysis through the interactive support environment where individual users can take advantage not only of the system’s capabilities to rapidly filter and locate relevant information, but also from each other’s actions and insights. The goal is to create an environment where groups of analysts can work together effectively on complex intelligence problems.Project manager and PI: Professor Tomek Strzalkowski

 

Social Robotics:

poster of project HITIQA

This awards brings together researchers and educators from UAlbany’s ILS, Rensselaer Polytechnic Institute, Schenectady County Community College, Union College and the Schenectady Museum and Suits-Bueche Planetarium. Students will utilize robots as a platform to learn key computer science concepts, begin to program, and learn about both hardware and software and the interplay between the two as part of a multi-school effort to deliver a unique educational experience for the Capital Region.
A Social robot is one that interacts and communicates with humans by following the social rules attached to its role. There are many aspects to the evolution of social robots, which need to draw on elements of design, psychology, cognitive science, communication and philosophy in addition to traditional Computer Science and Engineering principles. We are building a community of stakeholders in social robotics in the Capital Region, with four open workshops at a Schenectady Museum, bringing together academics, students, representatives from industry and members of the public to outline a program in social robotics. The outcome of this award will be the outline of a multi-agency program in social robotics, which can be implemented both locally and nationally.Project manager and PI: Nick Webb

 

DeER: Deliberative E-Rule Making Decision Facilitation Project

project COLLANE

By exploiting advances in question answering technology, discourse tracking, topic detection and summarization, we will present a suite of tools to enable online, collaborative deliberative decision making, providing a facilitation agent able to overcome traditional limitations in the online deliberative process.Project manager and PI: Dr. Peter Muhlberger

 

HITIQA : High-Quality Interactive Question Answering

poster of project HITIQA

This project is part of the three-phase AQUAINT Program. We are developing automated question-answering technology to assist intelligence analysts’ daily activities. Go to HITIQA official website to learn project progress.Project manager and PI: Professor Tomek Strzalkowski
Co-PI: Dr. Sharon G. Small

 

the Companions : Human Interface Technology for FP6

companion project

A Companion is intended as both a research program and an immediately feasible technology: a computational, persistent, personal presence. It is not a robot and the nature of its embodiment is not crucial: it could be a talking head on a TV screen, a persistent voice in a mobile phone, or a furry friend that sat beside an old person on a sofa and chatted to them about what TV they watch and reminded them to take their pills.Start date: November 2006
Duration: 5 Years
Website: http://www.companions-project.org/

 

AMITIES: Automated Multilingual Interaction with Information and Services(Demo)
poster of project ARMITIES

This multi-year project is funded jointly by the European Commission and the Defense Advanced Research Projects Agency (DARPA). Along with other partners of the trans-Atlantic consortium, we are developing automated multilingual call center applications through cutting-edge research into speech and natural language processing. ILS partners on AMITIES include the University of Sheffield, CNRS-LIMSI, Duke University, and VECSYS (credit kim). Go to AMITIES official website to learn project progress.Project PI and the consortium coordinator: Professor Tomek Strzalkowski

 

XDoX : Cross-Document Summarizer

poster of project XDoX

This project is a continuation of TIPSTER 3 contract, funded originally by DARPA since 1996, then by ARDA, and since 2000 as a subcontract to GE R&D Center. We are developing automated multi-document summarization applications for intelligence analysts.

Project PI: Professor Tomek Strzalkowski

 

Computational Logic and Reasoning

We develop computational logic and automated reasoning applications under projects funded by the Office of Naval Research and by the National Science Foundation.

Projects PI: Professor Paliath Narendran

 

MIll : Modeling Interorganizational Information Integration

Integrating and sharing information across government settings involves complex social and technological interactions. This project, performed by UAlbany’s Center for Technology in Government (CTG) with ILS support, studies problems of information integration initiatives in public safety and environmental management. CTG researchers are developing and testing dynamic models that explain the complex relationships between organizations and technology that can be used in government information integration projects.

Project PI: Dr. Sharon Dawes

 

Robotics

This project is offered to involve interested graduate and undergraduate students in the process of kicking off robotics research at SUNY Albany. This is a hands-on seminar where we will be developing demonstrations for 3 different applications involving SONY Aibo robotic dogs. Several Aibos plus SONY computers will be available. We will be using open source SDK for programming. The culmination will be RoboShow Symposium at SUNY Albany in early May 2004.

Project PI: Professor Tomek Strzalkowski