Igor Jugo

Intelligent tutoring systems for language learning

Intelligent tutoring systems (ITS) are able to provide a personalized approach to learning by assuming the role of a real teacher/expert who adapts and steers the learning process according to the specific needs of each learner. This is done by taking into account a number of learner features and deciding on the best action to follow at any point in the learning process. Within the field of computer assisted language learning (CALL), the “computer-as-a-tutor” modality has been widely accepted for some time now, although it has long been overshadowed by the “computer-as-a-tool” modality. This was mainly due to the observable lack of interactivity of language learning systems and the inability of technology to show “intelligence”. However, the development of artificial intelligence in general, and natural language processing, user modeling and ITSs in particular, gave impetus for the development of the field referred to as intelligent CALL (ICALL). The paper at hand outlines and briefly discusses the issues surrounding the development and use of ITSs for language learning, taking also into account the broader context of (I)CALL, and gives an overview of such systems already in use.

Assessing User Satisfaction with a System for e-Learning Based on Dialogue

Evaluating quality of an information system is an important activity in assuring system usage. The system has to be adapted to the needs of its users; otherwise, their dissatisfaction may lead to abandonment and financial loss for the system’s owner. This paper presents a study in assessing user satisfaction with a particular type of adaptive information system. The main aim is to develop and verify a measuring instrument for assessing user satisfaction with the system by taking system usability as the main indicator.

Analysis and Evaluation of Web Application Performance Enhancement Techniques

Performance is one of the key factors of web application success. Nowadays, users expect constant availability and immediate response following their actions. To meet those expectations, many new performance enhancement techniques have been created. We have identified almost twenty such techniques with various levels of implementation complexity. Each technique enhances one or more tiers of the application. Our goal was to measure the efficiency and effectiveness of such techniques when applied to finished products (we used three popular open source applications). We argue that it is possible to significantly enhance the performance of web applications by using even a small set of performance enhancement techniques. In this paper we analyse these techniques, describe our approach to testing and measuring their performance and present our results. Finally, we calculate the overall efficiency of each technique using weights given to each of the measured performance indicators, including the technique implementation time.

Corpora building and processing

Creativity is a basic feature of a language. Therefore, it is perfectly possible to create a completely new context that has never occurred before. This feature allows us to express our ideas, thoughts, knowledge and fears, but it also complicates the idea of human-machine communication. Since it became obvious that natural languages cannot be formalized and described as a whole, the idea of combining linguistic knowledge and corpora has arisen. The combination of these techniques has proven to give the best results and our research is based on that notion. Since data sparsity poses a huge problem, this work presents a practical solution in overcoming data sparsity problem and gives a detailed account of an advanced data processing technique.