Understanding and Exploiting Language Diversity
Publications | k.batsuren [at] unitn.it (Email)
Languages are well known to be diverse on all structural levels, from the smallest (phonemic) to the broadest (pragmatic). We propose a formal, quantitative method for the evaluation of the degree of generality or locality of linguistic phenomena. The mainstay of our approach is a multi-faceted measure of diversity in language sets. We apply our method to lexical semantics where we show how evidence of a high degree of universality within a given language set can be used to extend lexico-semantic resources in a precise, diversity-aware manner. We demonstrate the measures on a number of case studies including polysemy vs homonym and lexical gaps.
A Semantic Framework for Enabling Personal Data
Publications | enrico.bignotti [at] unitn.it (Email)
Nowadays, it is difficult to exploit personal data for providing services to users, since it must be “made sense” of them. Different communities focus on either of the representational or sensor data aspect of the problem. Our proposed solution is a methodological framework combining a reference ontology and sensor data to model people, their environment and their everyday contexts linking them to sensor data via statistical models. As evaluation points, we aim to ground the reference ontology in real life scenarios, while maintaining generality and interoperability, in addition to injecting semantics to improve sensor accuracy and provide tailored services to users.
Theory and Practice
Everyday huge amount of data is being captured and stored. This can either be due to technological advancement. This involves the release of data which differs in format, schema and standards from various types of user communities. The main challenge in this scenario lies in the integration of such diverse data and on the generator of knowledge. Various methodology for data modeling has been proposed. However, a few methodology elaborates the proceeding steps. As a result, there is lack of clarification how to handle different issues which occurs in the different phases of domain modeling. The aim of this research is to presents a scalable framework and a methodology for data modeling.
Semantic Image Interpretation
Let's teach machines to understand images
Semantic Image Interpretation (SII) is the task of extracting structured semantic descriptions from images. This task is suitable for Logic Tensor Networks (LTNs), a new Statistical Relational Learning framework which integrates neural networks with fuzzy logic. LTNs allows learning and reasoning with data and logical constraints. In my Ph.d. I study the application of LTNs to SII and its evaluation on the classification of image objects and visual relationships between them. The use of logical constraints improves the performance of purely data-driven approaches. Moreover, the logical constraints add robustness when the training labels are affected by errors.
The Use of Context in Shared Teaching Digital Materials
Hyeon Kyeong Hwang
Publications | hyeonkyeong.hwang [at] unitn.it (Email)
One of the greatest challenges of Web 2.0 is to find the relevant information to users’ needs with minimum effort and time. Though search engines have improved greatly in the recent years, search results depend on the textual search query, which does not reflect users’ search context. In particular, teachers find it difficult to retrieve suitable materials for their specific learning/teaching scenario. Tags are beneficial for improving search and retrieval but there has been no understanding as to which type of tags are useful and should be encouraged. In this research, we explore the types of important contextual meta-data in searching and retrieving shared teaching materials.
A multi-layer approach to social phenomena
modeling cultural phenomena and social influence
Publications | lorenzo.lucchini [at] unitn.it (Email)
In my research I model the dynamical properties of human behaviors using a multilayer network approach. An example is the mobility of culturally notable people: by modeling their reciprocal interaction and their spatial mobility I aim at a better understanding of the factors that determine the innovation and evolution in human culture.
Ontological Foundations for Strategic Analysis
Tiago Prince Sales
In competitive markets, companies need well-designed business strategies if they seek profitability. In order to drive the identification of such strategic issues, various frameworks have been proposed, which however, lack computational support for representing and reasoning with strategic information, for their concepts are informally defined and they rely exclusively on people analyze strategic issues. In my research, we address this issue through an interdisciplinary approach based on techniques from Formal Ontology, Enterprise Modelling and Strategic Management. Our goal is to develop a conceptual foundation for the development of computational tools to support strategic analysis.