Papers.

A Progress Report from the Linguistic Data Consortium: Recent Activities in Resource Creation and Distribution and the Development of Tools and Standards

Integrating Two Descriptions of Taxonomies with Materialization

Architecture For An Mpeg-7 Web Browser.

An MPEG-7 Database System and Application for Content-Based Management and Retrieval of Music.

Achieving Source Transparency in the UMLS Metathesaurus

Limited-Domain Speech-to-Speech Translation between English and Pashto

This paper describes a prototype system for near-real-time spontaneous, bidirectional translation between spoken English and Pashto, a language presenting many technological challenges because of its lack of resources, including both data and expert knowledge. Development of the prototype is ongoing, and we propose to demonstrate a fully functional version which shows the basic capabilities, though not yet their final depth and breadth.

TransType2 - An Innovative Computer-Assisted Translation System

Demonstration of the TransType2 computer-assisted translation system, which embeds a statistical MT engine inside an interactive translation environment so that the translator remains in control of output quality.

Finding Surface Lyapunov Functions Through Sum-of-Squares Programming

Control oriented modeling for enhanced yaw stability and vehicle steerability

Evaluating Development Alternatives for a High-Quality Stream Threatened by Urbanization

Automating Terrain Analysis: Algorithms for Intelligence Preparation of the Battlefield

Extending the ONESAF Testbed into a C4ISR Testbed

Towards an information infrastructure for the grid

The set constraint/CFL reachability connection in practice

Cloning-based context-sensitive pointer alias analysis using binary decision diagrams

Stitching

Object auras

Building Nutch: Open Source Search

Distributed regression: an efficient framework for modeling sensor network data

Unveiling the Transport

Self-managed decentralised systems using K-components and collaborative reinforcement learning

Third edition of the "XML and information retrieval" workshop first workshop on integration of IR and DB (WIRD) jointly held at SIGIR'2004, Sheffield, UK, July 29 th , 2004

Toward autonomic web services trust and selection

Emerging Web services standards enable the development of large-scale applications in open environments. In particular, they enable services to be dynamically bound. However, current techniques fail to address the critical problem of selecting the right service instances. Service selection should be determined based on user preferences and business policies, and consider the trustworthiness of service instances.

Accuracy vs. lifetime

Unifying collaborative and content-based filtering

Collaborative and content-based filtering are two paradigms that have been applied in the context of recommender systems and user preference prediction. This paper proposes a novel, unified approach that systematically integrates all available training information such as past user-item ratings as well as attributes of items or users to learn a prediction function. The key ingredient of our method is the design of a suitable kernel or similarity function between user-item pairs that allows simultaneous generalization across the user and item dimensions. We propose an on-line algorithm (JRank) that generalizes perceptron learning. Experimental results on the EachMovie data set show significant improvements over standard approaches.

Web page ranking using link attributes

Web page ranking using link attributes

A joint framework for collaborative and content filtering

This paper proposes a novel, unified, and systematic approach to combine collaborative and content-based filtering for ranking and user preference prediction. The framework incorporates all available information by coupling together multiple learning problems and using a suitable kernel or similarity function between user-item pairs. We propose and evaluate an on-line algorithm (JRank)that generalizes perceptron learning using this framework and shows significant improvement over other approaches.

An efficient clustering-based heuristic for data gathering and aggregation in sensor networks

Teaching data structures using competitive games.

Percolation Search in Power Law Networks: Making Unstructured Peer-to-Peer Networks Scalable

A framework and ontology for dynamic Web services selection

Current Web services standards lack the means for expressing a service's nonfunctional attributes - namely, its quality of service. QoS can be objective (encompassing reliability, availability, and request-to-response time) or subjective (focusing on user experience). QoS attributes are key to dynamically selecting the services that best meet user needs. This article addresses dynamic service selection via an agent framework coupled with a QoS ontology. With this approach, participants can collaborate to determine each other's service quality and trustworthiness.

WISDNA: an information visualization paradigm for XML

On the image content of the Chilean Web

Evolution of the Chilean Web structure composition

Optimization Flow Control with Estimation Error

Adapting Web Services in a Heterogeneous Environment

Federation and brokerage of learning objects and their metadata

Newsgroup Crowds and AuthorLines: visualizing the activity of individuals in conversational cyberspaces

The role of context in the integration of heterogeneous health care databases

Using Hermes-F: experiences with a framework for developing information retrieval applications

Fault Tolerant Computation on Ensemble Quantum Computers

Collaborative Reinforcement Learning of Autonomic Behaviour

Robust Connectivity of Networked Vehicles

Markov chain Monte Carlo data association for general multiple-target tracking problems

Agents Swarming in Semantic Spaces to Corroborate Hypotheses

Role of trust in e-business success

Scale-free and stable structures in complexad hocnetworks

One loop predictions of the finely tuned SSM

D-terms, unification, and the Higgs mass