Arianna Pipitone

Intelligent Agents supporting user interactions within self regulated learning processes

The paper focuses on the main advantages in the defnition and utilization of an open and modular e-learning software platform to support highly cognitive tasks performed by the main actors of the learning process. We present in detail the integration inside the platform of two intelligent agents devoted to talking with the student and to retrieving new information sources on the Web. The process is triggered as a reply to the system’s perception that the student feels discontented with the presented contents. The architecture is detailed, and some conclusions about the growth of the platform’s overall performance are expressed.

A Hidden Markov Model for Automatic Generation of ER Diagrams from OWL Ontology

Connecting ontological representations and data models is a crucial need in enterprise knowledge management, above all in the case of federated enterprises where corporate ontologies are used to share information coming from different databases. OWL to ERD transformations are a challenging research field in this scenario, due to the loss of expressiveness arising when OWL axioms have to be represented using ERD notation. In this paper we propose an innovative technique for estimating the most likely composition of ERD constructs that correspond to a given sequence of OWL axioms. We model such a process using a Hidden Markov Model (HMM) where the OWL inputs are the observable states, while ERD structures are the hidden states. Transition and emission probabilities have been set up heuristically through the analysis of a purposely defined grammar describing the ERD syntax, and all the OWL/ERD mapping rules presented in the literature. The theoretical model is explained in detail, a case study is exploited, and the experimental results are presented.

VEBO: Validation of E-R Diagrams through Ontologies and WordNet

In the semantic web vision, ontologies are building blocks for providing applications with a high level description of the operating environment in support of interoperability and semantic capabilities. The importance of ontologies in this respect is clearly stated in many works. Another crucial issue to increase the semantic aspect of web is to enrich the level of expressivity of database related data. Nowadays, databases are the primary source of information for dynamical web sites. The linguistic data used to build the database structure could be relevant for extracting meaningful information. In most cases, this type of information is not used for information retrieval. The work presented in this paper deals with an attempt to enrich a database structure using linguistic information. The purpose is twofold: the proposed approach can be used either to validate the database structure linguistically or at least to enrich information retrieval with structural information. In this paper the first goal is pursued by the construction of the VEBO system that is used to validate database entity-relation diagrams through semi-automatic creation and enrichment of ontology.

QuASIt: A Cognitive Inspired Approach to Question Answering for the Italian Language

In this paper we present QuASIt, a Question Answering System for the Italian language, and the underlying cognitive architecture. The term cognitive is meant in the procedural semantics perspective, which states that the interpretation and/or production of a sentence requires the execution of some cognitive processes over both a perceptually grounded model of the world, and a linguistic knowledge acquired previously. We attempted to model these cognitive processes with the aim to make an artificial agent able both to understand and produce natural language sentences. The agent runs these processes on its inner domain representation using the linguistic knowledge also. In this sense, QuASIt is both a rule-based and ontology-based question answering system. In the model, rules are aimed at understanding the query in terms of the linguistic typology of the question, and enabling its semantic processing as regards the search for the answer in the structured knowledge from DBPedia Italian project. Also the free explicative text in support of the query is analyzed if available. QuASIt attempts to answer for both multiple choice and essay questions. The model is presented, the implementation of the system is detailed, and some experiments are discussed.

Semantic sense extraction from Wikipedia pages

This paper discusses a modality to access and to organize unstructured contents related to a particular topic coming from the access to Wikipedia pages. The proposed approach is focused on the acquisition of new knowledge from Wikipedia pages and is based on the definition of useful patterns able to extract and identify novel concepts and relations to be added in the knowledge base. We proposes a method that uses information from the wiki pages structure. According to the different part of the page we define different strategies to obtain new concepts or relation between them. We analyze not only structure but text directly to obtain relations and concepts and to extract the type of relations to be incorporated in a domain ontology. The purpose is to use the obtained information in an intelligent tutoring system to improve his capabilities in dialogue management with users.

WikiArt: An Ontology-Based Information Retrieval System for Arts

The paper presents WikiArt, a new system integrating three distinct types of contents about the art: data, information, and knowledge, to generate automatically thematic paths to consult all its contents. WikiArt is a wiki, allowing to manage cooperatively documents about artists, artworks, artistic movements or techniques, and so on. It is also an expert system, provided with an ontology about arts, with which it is able to plan possible different ways of consulting and browsing its contents. This ability is made possible by a second part of the ontology of the system, describing a collection of criteria regarding how to plan thematic paths, and by a set of rules followed by the expert system to carry out this task. WikiArt is not a semantic wiki, because the ontology has not been employed to tag semantically the documents by the authors. But only their subjects. Our efforts are now devoted to the extension of the system to make it a semantic wiki too.

HOWERD: A Hidden Markov Model for Automatic OWL-ERD Alignment

The HOWERD model for estimating the most likely alignment between an OWL ontology and an Entity Relation Diagram (ERD) is presented. Automatic alignment between relational schema and ontology represents a big challenge in Semantic Web research due to the different expressiveness of these representations. A relational schema is less expressive than the ontology, this is a non trivial problem when accessing data via an ontology and for ontology storing by means of a relational schema. Existent alignment methodologies fail in loosing some contents of the involved representations because the ontology captures more semantic information, and several elements are left unaligned. HOWERD relies on a Hidden Markov Model (HMM) to estimate the most likely sequence of ERD symbols in a relational schema that correspond to the constructs of an OWL axiom in the ontology to be aligned. Such constructs are the observable states in the HMM, while hidden states are modeled as the symbols of a context free grammar defined purposely for describing the input ERD lexically.

Fostering Teacher-Student Interaction and Learner Autonomy by the I-TUTOR Maps

The paper analyses the use of an automatically generated map as a mediator; that map visually represents the study domain of a university course and fosters the co-activity between teachers and students. In our approach the role of the teacher is meant as a mediator between the student and knowledge. The mediation and not the transmission highlights a process in which theres no deterministic relation between teaching and learning. Learning is affected by the students previous experiences, their own modalities of acquisition and by the inputs coming from the environment. The learning path develops when the teachers and the students visions approach and, partly, overlap. In this case we have co-activity. The teacher uses artifacts-mediators in such a process Bruner. The automatically generated map can be considered a mediator. The paper describes the experimentation of the artifact to check if its use fosters: 1 the elicitation of the different subjects perspectives different students and the teachers, and 2 the structural coupling that is the creation of an empathic process between the perspectives of the teacher and the student as the way to enable co-activity processes between teaching and learning..

Automatic Concept Maps Generation in Support of Educational Processes

A VLE is a system where three main actors can be devised: the teacher in the role of instructional designer, the tutor, and the stu- dent. Instructional designers need easy interaction for specifying the course domain structure to the system, and for controlling how well the learning materials agree to such a structure. Tutors need tools for having a holistic perception of the evolution of single students and/or groups in the VLE during the learning process. Finally, students need self regulation in terms of controlling their learning rate, reflect on their learning strategies, and comparing with other people in the class. In this work we claim that sharing an implicit representation of the knowledge about the course domain between all these actors can meet the requirements stated before, and we present a tool that has been developed as part of the I-TUTOR project according to our claim. The tool analyzes a suitable document corpus describing the course domain, and generates a semantic space, which in turn is displayed as a 2D zoomable map. All the relevant concepts of the domain are depicted in the map, and learning materials can be browsed through the tool. Also the texts generated by students during the learning process as well as their social activities inside the VLE can be placed in the map. The motivations of the work are reported as well as the underlying AI techniques, and the whole system is explained in detail.

An A* Based Semantic Tokenizer for Increasing the Performance of Semantic Applications

Semantic Applications (SAs) makes use of ontologies and their performance can depend on the syntactic labels of the modeled entities, even if several approaches have been devised to formalize ontologies, no formal approaches have been devised for naming their constituents, which look as long word concatenations without any particular separation. We present a novel semantic tokenizer that finds the sub-words through an application of the A based search algorithm, the A functions rely on a set of linguistic criteria and on the meta-cognitive perspective of the activity of reading.