Noemi Scarpato

Semantic turkey: a browser-integrated environment for knowledge acquisition and management

With the continued growth of online semantic information, the processes of searching and managing this massive scale and heterogeneous content have become increasingly challenging. In this work, we present PowerAqua, an ontologybased Question Answering system that is able to answer queries by locating and integrating information, which can be distributed across heterogeneous semantic resources. We provide a complete overview of the system including: the research challenges that it addresses, its architecture, the evaluations that have been conducted to test it, and an in-depth discussion showing how PowerAqua effectively supports users in querying and exploring Semantic Web content.Born four years ago as a Semantic Web extension for the web browser Firefox, Semantic Turkey pushed forward the traditional concept of links&folders-based bookmarking to a new dimension, allowing users to keep track of relevant information from visited web sites and to organize the collected content according to standard or personally defined ontologies. Today, the tool has broken the boundaries of its original intents and can be considered, under every aspect, an extensible platform for knowledge management and acquisition. The semantic bookmarking and annotation facilities of Semantic Turkey are now supporting just a part of a whole methodology where different actors, from domain experts to knowledge engineers, can cooperate in developing, building and populating ontologies while navigating the Web.

Semi-automatic Generation of GUIs for RDF Browsing

In this paper we present an approach to automatic generation of GUI for browsing of RDF data based on observation of existing forms and their adaptation to available RDF graphs. The objective of such an approach is the rapid prototyping of forms and their associated queries by exploiting the vast amount examples that is already available from the Web, and trying to automate those steps requiring human intervention (form template extraction, query specification) for customizing found examples to developer’s specific needs.

STIA: Experience of Semantic Annotation in Jurisprudence Domain

In this work we present STIA: a tool for semantic annotation in the Jurisprudence domain. The tool offers an easy interface to domain experts (lawyers, administrative, researchers, …) for annotating relationships of pertinence between portions of text from different laws covering similar topics/circumstances/events. These annotations either constitute a resource on their own (which can be used in the context of semantic search engines to improve retrieval of related laws) as well as a precious feed for tools aiming at automatically extracting more of the above relationships.

Probabilistic Ontology Learner in Semantic Turkey

In this paper we present the Semantic Turkey Ontology Learner (ST-OL), an incremental ontology learning system, that follows two main ideas: (1) putting final users in the learning loop; (2) using a probabilistic ontology learning model that exploits transitive relations for inducing better extraction models.

RISK: A Random Optimization Interactive System Based on Kernel Learning for Predicting Breast Cancer Disease Progression

Evaluating disease progression risk is a key issue in medicine that has been revolutionized by the advent of machine learning approaches and the wide availability of medical data in electronic form. It is time to provide physicians with near-to-the-clinical-practice and effective tools to spread this important technological innovation. In this paper, we describe RISK, a web service that implements a multiple kernel learning approach for predicting breast cancer disease progression. We report on the experience of the BIBIOFAR project where RISK Web Predictor has been developed and tested. Results of our system demonstrate that this kind of approaches can effectively support physicians in the evaluation of risk.