Chiara Del Vescovo

The modular structure of an ontology: atomic decomposition

Extracting a subset of a given ontology that captures all the ontologys knowledge about a specified set of terms is a well-understood task. This task can be based, for instance, on locality-based modules. However, a single module does not allow us to understand neither topicality, connectedness, structure, or superfluous parts of an ontology, nor agreement between actual and intended modeling. The strong logical properties of locality-based modules suggest that the family of all such modules of an ontology can support comprehension of the ontology as a whole. However, extracting that family is not feasible, since the number of locality-based modules of an ontology can be exponential w.r.t. its size. In this paper we report on a new approach that enables us to efficiently extract a polynomial representation of the family of all locality-based modules of an ontology. We also describe the fundamental algorithm to pursue this task, and report on experiments carried out and results obtained.

Decomposition and modular structure of BioPortal ontologies

We present the first large scale investigation into the modular structure of a substantial collection of state-of-the-art biomedical ontologies, namely those maintained in the NCBO BioPortal repository. Using the notion of Atomic Decomposition, we partition BioPortal ontologies into logically coherent subsets (atoms), which are related to each other by a notion of dependency. We analyze various aspects of the resulting structures, and discuss their implications on applications of ontologies. In particular, we describe and investigate the usage of these ontology decompositions to extract modules, for instance, to facilitate matchmaking of semantic Web services in SSWAP (Simple Semantic Web Architecture and Protocol). Descriptions of those services use terms from BioPortal so service discovery requires reasoning with respect to relevant fragments of ontologies (i.e., modules). We present a novel algorithm for extracting modules from decomposed BioPortal ontologies which is able to quickly identify atoms that need to be included in a module to ensure logically complete reasoning. Compared to existing module extraction algorithms, it has a number of benefits, including improved performance and the possibility to avoid loading the entire ontology into memory. The algorithm is also evaluated on BioPortal ontologies and the results are presented and discussed.

Kernel-based relation extraction from investigative data

In a specific process of business intelligence, i.e. investigation on organized crime, empirical language processing technologies can play a crucial role. In the data used on investigative activities, such as police interrogatory or electronic eavesdropping and wiretap, it is customary to find out expressions in non conventional languages as dialects, slangs or coded words. The recognition and storage of complex relations among subjects mentioned in these sources is a very difficult and time consuming task, ultimately based on pools of experts. We discuss here an inductive relation extraction platform that opens the way to much cheaper and consistent workflows. SVMs here are employed to produce a set of possible interpretations for domain relevant concepts. An ontology population process is here realized, where further reasoning can be applied to proof the overall consistency of the extracted information. The empirical investigation presented here shows that accurate results, comparable to the expert teams, can be achieved, and parametrization allows to fine tune the system behavior for fitting the specific domain requirements.

Kernel-Based Learning for Domain-Specific Relation Extraction

In a specific process of business intelligence, i.e. investigation on organized crime, empirical language processing technologies can play a crucial role. The analysis of transcriptions on investigative activities, such as police interrogatories, for the recognition and storage of complex relations among people and locations is a very difficult and time consuming task, ultimately based on pools of experts. We discuss here an inductive relation extraction platform that opens the way to much cheaper and consistent workflows. The presented empirical investigation shows that accurate results, comparable to the expert teams, can be achieved, and parametrization allows to fine tune the system behavior for fitting domain-specific requirements.