CSIEC (Computer Simulation in Educational Communication), is not only an intelligent web-based human-computer dialogue system with natural language for English instruction, but also a learning assessment system for learners and teachers. Its multiple functions—including grammar-based gap filling exercises, scenario show, free chatting and chatting on a given topic—can satisfy the various requirements for students with different backgrounds and learning abilities. After a brief explanation of the conception of our dialogue system, as well as a survey of related works, we will illustrate the system structure, and describe its pedagogical functions with the underlying AI techniques in detail such as NLP and rule-based reasoning. We will summarize the free Internet usage within a six month period and its integration into English classes in universities and middle schools. The evaluation findings about the class integration show that the chatting function has been improved and frequently utilized by the users, and the application of the CSIEC system on English instruction can motivate the learners to practice English and enhance their learning process. Finally, we will conclude with potential improvements.

The hardness of finite domain Constraint Satisfaction Problems (CSPs) is a very important research area in Constraint Programming (CP) community. However, this problem has not yet attracted much attention from the researchers in the association rule mining community. As a popular data mining technique, association rule mining has an extremely wide application area and it has already been successfully applied to many interdisciplines. In this paper, we study the association rule mining techniques and propose a cascaded approach to extract the interesting patterns of the hard CSPs. As far as we know, this problem is investigated with the data mining techniques for the first time. Specifically, we generate the random CSPs and collect their characteristics by solving all the CSP instances, and then apply the data mining techniques on the data set and further to discover the interesting patterns of the hardness of the randomly generated CSPs

The problem of detecting terms that can be interesting to the advertiser is considered. If a company has already bought some advertising terms which describe certain services, it is reasonable to find out the terms bought by competing companies. A part of them can be recommended as future advertising terms to the company. The goal of this work is to propose better interpretable recommendations based on FCA and association rules.

In rules considered in this paper, the conclusion may contain existentially quantified variables, which makes reasoning tasks (as deduction) non-decidable. These rules have the same logical form as TGD (tuple generating dependencies) in databases and as conceptual graph rules. We extend known decidable cases by combining backward and forward chaining schemes, in association with a graph that captures exactly the notion of dependency between rules. Finally, we draw a map of known decidable cases, including an extension obtained by combining our approach with very recent results on TGD.

When mathematicians present proofs they usually adapt their explanations to their didactic goals and to the (assumed) knowledge of their addressees. Modern automated theorem provers, in contrast, present proofs usually at a fixed level of detail (also called granularity). Often these presentations are neither intended nor suitable for human use. A challenge therefore is to develop user- and goal-adaptive proof presentation techniques that obey common mathematical practice. We present a flexible and adaptive approach to proof presentation that exploits machine learning techniques to extract a model of the specific granularity of proof examples and employs this model for the automated generation of further proofs at an adapted level of granularity.

Design, evaluation and refinement of intelligent systems was a popular topic at FLAIRS 2008. More and more authors have realized that the lack of systematic methods and formal techniques for the design, the evaluation, and the refinement are often important reasons for not using AI systems in practice. The first contributions in this field were limited to classical AI approaches such as rule-based systems. Actually, more and more papers regarding nonclassical types of systems (like case-based systems, for example), knowledge processing principles (learning principles, for example), and intelligent behavior (game strategies, for example) are published. Rule-based systems are still a subject of the track, but the focus is widened from their verification and validation towards also covering the design issue.

In this paper certain knowledge and software engineering methods integration issues are discussed. The principal idea is to consider an effective design and implementation framework for rule design with UML, and implementation with Java. The solution proposed in the paper consists of using a custom knowledge engineering design method for rules in the design stage. The rule base is then transformed to UML behavioral diagrams, which can be considered a visual encoding. The rule implementation involves the serialization to Java language using classes representing the decision tables grouping rules sharing the same attributes.

The success of knowledge discovery in real-world domains often depends on our ability to handle data imperfections. Here we study this problem in the framework of association mining, seeking to identify frequent itemsets in transactional databases where the presence of some items in a given transaction is unknown. We want to use the frequent itemsets to predict "missing items": based on the partial contents of a shopping cart, predict what else will be added. We describe a technique that addresses this task, and report experiments illustrating its behavior.

Evaluating changes in documentation of technical products is a key issue in knowledge management. A product may be declined in different versions and one way to evaluate changes is to compare the sets of documents which describe each version. The aim of this paper is to propose a framework for exhibiting changes between sets of documents. This framework is based on the representation of the sets of documents in terms of association rules and on the definition of first order predicates for reasoning with these association rules. The aim of the reasoning stage is to exhibit the differences between the sets of documents. These predicates show what rules are specific to a corpus or how differs the usage of concepts appearing in the associations rules. The framework is  experimented with the comparison of two corpuses of documents which describe documentation about two different versions of a spatial component.

In this search, we focused on supervised learning task using association rules algorithms (association based classification). These algorithms, developed in unsupervised learning, extract all the rules whose the support and confidence exceed a prefixed threshold support. After extracting the frequent itemsets, (i.e their support exceeds the threshold support), algorithms subdivide these itemsets to build the rules, and keep only the rules whose confidence exceeds the threshold confidence. The extraction of class association rules, using these algorithms, have several problems, because of the rules' a posteriori filtering. In the first stage, one extracts useless frequent itemsets, those which do not contain class, whereas the second stage can be simplified, since an itemset containing the class gives place only to only one class rule. In order to be able to work with a low threshold support, we propose FCP-Growth an adaptation of FP-Growth which eliminates the frequent itemsets not containing a class. Moreover, to make the minority class be in advantage during the construction of the class itemsets, we adapt the threshold support, in order to use the same threshold support inside each class.