A fundamental requirement of any task-oriented dialogue system is the ability to generate object descriptions that refer to objects in the task domain. The subproblem of content selection for object descriptions in task-oriented dialogue has been the focus of much previous work and a large number of models have been proposed. In this paper, we use the annotated COCONUT corpus of task-oriented design dialogues to develop feature sets based on Dale and Reiter's (1995) incremental model, Brennan and Clark's (1996) conceptual pact model, and Jordan's (2000b) intentional influences model, and use these feature sets in a machine learning experiment to automatically learn a model of content selection for object descriptions. Since Dale and Reiter's model requires a representation of discourse structure, the corpus annotations are used to derive a representation based on Grosz and Sidner's (1986) theory of the intentional structure of discourse, as well as two very simple representations of discourse structure based purely on recency. We then apply the rule-induction program RIPPER to train and test the content selection component of an object description generator on a set of 393 object descriptions from the corpus. To our knowledge, this is the first reported experiment of a trainable content selection component for object description generation in dialogue. Three separate content selection models that are based on the three theoretical models, all independently achieve accuracies significantly above the majority class baseline (17%) on unseen test data, with the intentional influences model (42.4%) performing significantly better than either the incremental model (30.4%) or the conceptual pact model (28.9%). But the best performing models combine all the feature sets, achieving accuracies near 60%. Surprisingly, a simple recency-based representation of discourse structure does as well as one based on intentional structure. To our knowledge, this is also the first empirical comparison of a representation of Grosz and Sidner's model of discourse structure with a simpler model for any generation task.

Running services in many small processes improves fault tolerance since any number of services can fail due to programming faults without affecting the rest of the system. While it is clearly important to be able to handle a wide range of failures, application authors should not be required to implement routines to test and react in every known mode of failure for every application, even if the failures are abstracted to a common interface. Thus, the framework also provides transparent fault-tolerance to users of system services. Errors in software and hardware are detected, and corrective action is taken. Services can be restarted or removed from the system, and clients are reconnected to the same service or to another service implementing the same interface without intervention from the application programmer. The Washington University team successfully demonstrated its failure-tolerant framework on its robot, Lewis (figure 6).

Data integration is the problem of combining data residing at different autonomous, heterogeneous sources and providing the client with a unified, reconciled global view of the data. We discuss dataintegration systems, taking the abstract viewpoint that the global view is an ontology expressed in a class-based formalism. We resort to an expressive description logic, ALCQI, that fully captures classbased representation formalisms, and we show that query answering in data integration, as well as all other relevant reasoning tasks, is decidable. However, when we have to deal with large amounts of data, the high computational complexity in the size of the data makes the use of a fullfledged expressive description logic infeasible in practice. This leads us to consider DL-Lite, a specifically tailored restriction of ALCQI that ensures tractability of query answering in data integration while keeping enough expressive power to capture the most relevant features of class-based formalisms.

AAAI presented the AAAI-04 workshop program on July 25-26, 2004 in San Jose, California. This program included twelve workshops covering a wide range of topics in artificial intelligence. The titles of the workshops were as follows: (1) Adaptive Text Extraction and Mining; (2) Agent Organizations: Theory and Practice; (3) Anchoring Symbols to Sensor Data; (4) Challenges in Game AI; (5) Fielding Applications of Artificial Intelligence; (6) Forming and Maintaining Coalitions in Adaptive Multiagent Systems; (7) Intelligent Agent Architectures: Combining the Strengths of Software Engineering and Cognitive Systems; (8) Learning and Planning in Markov Processes -- Advances and Challenges; (9) Semantic Web Personalization; (10) Sensor Networks; (11) Spatial and Temporal Reasoning; and (12) Supervisory Control of Learning and Adaptive Systems.

XML, web services, and the semantic web have opened the door for new and exciting informationintegration applications. Information sources on the web are controlled by different organizations or people, utilize different text formats, and have varying inconsistencies. Therefore, any system that integrates information from different data sources must identify common entities from these sources. Data from many data sources on the web does not contain enough information to link the records accurately using state-of-the-art record-linkage systems. However, it is possible to exploit secondary data sources on the web to improve the recordlinkage process. We present an approach to accurately and automatically match entities from various data sources by utilizing a state-of-the-art record-linkage system in conjunction with a data-integration system. The data-integration system is able to automatically determine which secondary sources need to be queried when linking records from various data sources. In turn, the record-linkage system is then able to utilize this additional information to improve the accuracy of the linkage between datasets.

Posters, and the AAAI/ SIGART consist of two phases: a qualification Doctoral Consortium. Please visit the round and a runoff competition. A AAAI is pleased to announce the AAAI-05 web site periodically for upto-date $10,000 prize will be awarded to the launch of the First Annual Artificial information. We hope you will winning entrant. The competition is Intelligence for Interactive Digital join us in Pittsburgh!

The Sixth International Conference on Enterprise Information Systems (ICEIS) was held in Porto, Portugal; previous venues were in Spain, France, and the United Kingdom. Since its inception in 1999, ICEIS has grown steadily, and is now one of the largest international conferences in the area of information systems. In 2004, more than 600 papers were submitted to the conference and its ten satellite workshops. One of the interesting features of this conference is the high number of invited speakers. In 2004, eighteen keynote speakers were featured at ICEIS and its workshops.

There has been increased interest in devising learning techniques that combine unlabeled data with labeled data - i.e. semi-supervised learning. However, to the best of our knowledge, no study has been performed across various techniques and different types and amounts of labeled and unlabeled data. Moreover, most of the published work on semi-supervised learning techniques assumes that the labeled and unlabeled data come from the same distribution. It is possible for the labeling process to be associated with a selection bias such that the distributions of data points in the labeled and unlabeled sets are different. Not correcting for such bias can result in biased function approximation with potentially poor performance. In this paper, we present an empirical study of various semi-supervised learning techniques on a variety of datasets. We attempt to answer various questions such as the effect of independence or relevance amongst features, the effect of the size of the labeled and unlabeled sets and the effect of noise. We also investigate the impact of sample-selection bias on the semi -supervised learning techniques under study and implement a bivariate probit technique particularly designed to correct for such bias.

We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. We derive upper and lower relative loss bounds for a class of universal learning algorithms involving aswitching dynamics over the choice of the experts. On the basis of the performance bounds we provide the optimal a priori discretization forlearning the parameter that governs the switching dynamics. We demonstrate the new algorithm in the context of wireless networks.

We describe a pattern acquisition algorithm that learns, in an unsupervised fashion, a streamlined representation of linguistic structures from a plain natural-language corpus. This paper addresses the issues of learning structured knowledge from a large-scale natural language data set, and of generalization to unseen text. The implemented algorithm represents sentences as paths on a graph whose vertices are words (or parts of words). Significant patterns, determined by recursive context-sensitive statistical inference, form new vertices. Linguistic constructions are represented by trees composed of significant patterns and their associated equivalence classes. An input module allows the algorithm to be subjected to a standard test of English as a Second Language (ESL) proficiency. The results are encouraging: the model attains a level of performance considered to be "intermediate" for 9th-grade students, despite having been trained on a corpus (CHILDES) containing transcribed speech of parents directed to small children.