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.

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.

Semantic integration has been a long-standing challenge for the database community. It has received steady attention over the past two decades, and has now become a prominent area of database research. In this article, we first review database applications that require semantic integration and discuss the difficulties underlying the integration process. We then describe recent progress and identify open research issues. We focus in particular on schema matching, a topic that has received much attention in the database community, but also discuss data matching (for example, tuple deduplication) and open issues beyond the match discovery context (for example, reasoning with matches, match verification and repair, and reconciling inconsistent data values). For previous surveys of database research on semantic integration, see Rahm and Bernstein (2001); Ouksel and Seth (1999); and Batini, Lenzerini, and Navathe (1986).

We propose the use of application semantics to enhance the process of semantic reconciliation. Application semantics involves those elements of business reasoning that affect the way concepts are presented to users: their layout, and so on. In particular, we pursue in this article the notion of precedence, in which temporal constraints determine the order in which concepts are presented to the user. Existing matching algorithms use either syntactic means (such as term matching and domain matching) or model semantic means, the use of structural information that is provided by the specific data model to enhance the matching process. The novelty of our approach lies in proposing a class of matching techniques that takes advantage of ontological structures and application semantics. As an example, the use of precedence to reflect business rules has not been applied elsewhere, to the best of our knowledge. We have tested the process for a variety of web sites in domains such as car rentals and airline reservations, and we share our experiences with precedence and its limitations.

In this paper we concentrate on the resolution of the lexical ambiguity that arises when a given word has several different meanings. This specific task is commonly referred to as word sense disambiguation (WSD). The task of WSD consists of assigning the correct sense to words using an electronic dictionary as the source of word definitions. We present two WSD methods based on two main methodological approaches in this research area: a knowledge-based method and a corpus-based method. Our hypothesis is that word-sense disambiguation requires several knowledge sources in order to solve the semantic ambiguity of the words. These sources can be of different kinds--- for example, syntagmatic, paradigmatic or statistical information. Our approach combines various sources of knowledge, through combinations of the two WSD methods mentioned above. Mainly, the paper concentrates on how to combine these methods and sources of information in order to achieve good results in the disambiguation. Finally, this paper presents a comprehensive study and experimental work on evaluation of the methods and their combinations.

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.

Argumentation is based on the exchange and valuation of interacting arguments, followed by the selection of the most acceptable of them (for example, in order to take a decision, to make a choice). Starting from the framework proposed by Dung in 1995, our purpose is to introduce 'graduality' in the selection of the best arguments, i.e., to be able to partition the set of the arguments in more than the two usual subsets of 'selected' and 'non-selected' arguments in order to represent different levels of selection. Our basic idea is that an argument is all the more acceptable if it can be preferred to its attackers. First, we discuss general principles underlying a 'gradual' valuation of arguments based on their interactions. Following these principles, we define several valuation models for an abstract argumentation system. Then, we introduce 'graduality' in the concept of acceptability of arguments. We propose new acceptability classes and a refinement of existing classes taking advantage of an available 'gradual' valuation.

We study the properties of the MDL (or maximum penalized complexity) estimator for Regression and Classification, where the underlying model class is countable. We show in particular a finite bound on the Hellinger losses under the only assumption that there is a "true" model contained in the class. This implies almost sure convergence of the predictive distribution to the true one at a fast rate. It corresponds to Solomonoff's central theorem of universal induction, however with a bound that is exponentially larger.

In this paper, we confront the problem of applying reinforcement learning to agents that perceive the environment through many sensors and that can perform parallel actions using many actuators as is the case in complex autonomous robots. We argue that reinforcement learning can only be successfully applied to this case if strong assumptions are made on the characteristics of the environment in which the learning is performed, so that the relevant sensor readings and motor commands can be readily identified. The introduction of such assumptions leads to strongly-biased learning systems that can eventually lose the generality of traditional reinforcement-learning algorithms. In this line, we observe that, in realistic situations, the reward received by the robot depends only on a reduced subset of all the executed actions and that only a reduced subset of the sensor inputs (possibly different in each situation and for each action) are relevant to predict the reward. We formalize this property in the so called 'categorizability assumption' and we present an algorithm that takes advantage of the categorizability of the environment, allowing a decrease in the learning time with respect to existing reinforcement-learning algorithms. Results of the application of the algorithm to a couple of simulated realistic-robotic problems (landmark-based navigation and the six-legged robot gait generation) are reported to validate our approach and to compare it to existing flat and generalization-based reinforcement-learning approaches.