Anca Marginean

Question answering over biomedical linked data with Grammatical Framework

The blending of linked data with ontologies leverages the access to data. GFMed introduces grammars for a controlled natural language targeted towards biomedical linked data and the corresponding controlled SPARQL language. The grammars are described in Grammatical Framework and introduce linguistic and SPARQL phrases mostly about drugs, diseases and relationships between them. The semantic and linguistic chunks correspond to Description Logic constructors. Problems and solutions for querying biomedical linked data with Romanian, besides English, are also considered in the context of GF.

CoNtRol: an open source framework for the analysis of chemical reaction networks

UNLABELLED We introduce CoNtRol, a web-based framework for analysis of chemical reaction networks (CRNs). It is designed to be both extensible and simple to use, complementing existing CRN-related tools. CoNtRol currently implements a number of necessary and/or sufficient structural tests for multiple equilibria, stable periodic orbits, convergence to equilibria and persistence, with the potential for incorporation of further tests. AVAILABILITY AND IMPLEMENTATION Reference implementation: reaction-networks.net/control/. Source code and binaries, released under the GPLv3: reaction-networks.net/control/download/. Documentation: reaction-networks.net/wiki/CoNtRol.

LELA - a natural language processing system for Romanian tourism

This paper presents a commercial semantic-based system for the Romanian tourism. The Lela system exploits both open linked data from Romanian and international sources, and also proprietary databases in the tourism domain. We present the process of creating the linked data set, based on: i) engineering the LELA Romanian tourism ontology, and ii) populating the ontology by linking open data. The system also provides a natural language interface for the Romanian language. The queries are automatically translated into SPARQL based on a controlled vocabulary derived from the Lela ontology.

A multi-agent approach towards cooperative overtaking in vehicular networks

This paper deals with the integration of agent technology in the emerging field of vehicular networks. The agents are empowered with domain knowledge and they can perform geospatial and temporal reasoning. For the domain knowledge we developed a vehicular network ontology. The geospatial reasoning is performed with AllegroGraph, while event reasoning in RacerPro. The vehicle overtaking scenario is used to exemplify our solution.

Service monitoring with ontology based expectations

Addressing inarticulate needs in addition to basic needs satisfies better the customer. Therefore, in assessing the quality of a service, we propose a blending between the background knowledge of the client, his current expectations, concrete observations on its interaction with the service, and interpretations of these observations. The pair description-situation from foundational ontology Dolce + DnS supports an homogeneous and integrated representation of both direct observations from SOAP messages and also interpretations of these observations according to the current context and knowledge. Expectations are the instrument for monitoring the clients interaction with the service, and for assessing its perceived quality of the service.

Z-based agents for service oriented computing

Ensuring reliability and adaptability of web services represents one of the main prerequisites for a larger acceptance of web services technology. We present an agent based framework to model the global behavior of atomic e-service and their composition using Z. We consider failures associated with web services and we try to handle runtime exceptions through formal methods for specification and verification of a composite service. In addition, our framework enforces the quality of services, in terms of answer time, by providing Z-agents responsible for these aspects.

Towards Improving Situation Awareness during Emergency Transportation through Ambulance-2-X Communication and Semantic Stream Reasoning

With the recent introduction of the eCall system, the cars involved in accidents exchange relevant information directly with the emergency healthcare services. For road safety, Vehicular Ad-hoc Networks can be used to exchange safety information between cars and ambulances, via vehicle-2-x communication. In this paper, we exploit recent advances in vehicle-2-x communication and the advantages of knowledge representation and reasoning in order to deploy cooperative communication for medical emergency services. The developed system continuously matches data retrieved from inter-vehicular communication with structured knowledge from vehicular ontologies and open street maps.

Romanian2SPARQL: A Grammatical Framework approach for querying Linked Data in Romanian

SPARQL queries have become the current state of the art for querying linked open data repositories. Given the difficulties to create such queries by non-expert users, interfaces that accept questions in natural language and convert them to SPARQL are one solution to this problem. We developed a translator for Romanian natural language to SPARQL. The system exploits the conceptual power of the Grammatical Framework library and the Haskell programming language. The system is validated in the Romanian cultural domain against various Linked Data Sources, including DBpedia.

Towards Lexicalization of DBpedia Ontology with Unsupervised Learning and Semantic Role Labeling

Filling the gap between natural language expressions and ontology concepts or properties is the new trend in Semantic Web. Ontology lexicalization introduces a new layer of lexical information for ontology properties and concepts. We propose a method based on unsupervised learning for the extraction of the potential lexical expressions of DBpedia propertiesfrom Wikipedia text corpus. It is a resource-driven approach that comprises three main steps. The first step consists of the extraction of DBpedia triples for the aimed property followed by the extraction of Wikipedia articles describing the resources from these triples. In the second step, sentences mostly related to the property are extracted from the articles and they are analyzed with a Semantic Role Labeler resulting in a set of SRL annotated trees. In the last step, clusters of expressions are built using spectral clustering based on the distances between the SRL trees. The clusters with the least variance are considered to be relevant for the lexical expressions of the property.

Using Domain Specific Hierarchical Good Practice for Ranking Service Compositions

We propose a method for ranking the service compositions according to the good practice of each domain. Knowledge about good practice is modeled in a hierarchical manner inspired from Hierarchical Task Networks. In describing the good practice knowledge we give a model for HTN in N3 notation and we enhanced it with an importance value. Each candidate service composition is checked against good practice in a model checking style. A candidate composition is a sequence of services. The candidate composition is compared to the constraints defined in good practice and is considered good if for each simple task the most important constraints are fulfilled.