Simona Colucci

Concept abduction and contraction for semantic-based discovery of matches and negotiation spaces in an e-marketplace

In this paper, we present a Description Logic approach - fully compliant with the Semantic web vision and technologies - to extended matchmaking between demands and supplies in a semantic-enabled Electronic Marketplace, which allows the semantic-based treatment of negotiable and strict requirements in the demand/supply descriptions. To this aim, we exploit two novel non-standard Description Logic inference services, Concept Contraction - which extends satisfiability - and Concept Abduction - which extends subsumption. Based on these services, we devise algorithms, which allow to find negotiation spaces and to determine the quality of a possible match, also in the presence of a distinction between strictly required and optional elements. Both the algorithms and the semantic-based approach are novel, and enable a mechanism to boost logic-based discovery and negotiation stages within an e-marketplace. A set of simple experiments confirm the validity of the approach.

A Logic-Based Approach for Matching User Profiles

Several applications require the matching of user profiles, e.g., job recruitment or dating systems. In this paper we present a logical framework for specifying user profiles that allows profile description to be incomplete in the parts that are unavailable or are considered irrelevant by the user. We present an algorithm for matching demands and supplies of profiles, taking into account incompleteness of profiles and incompatibility between demand and supply. We specialize our framework to dating services; however, the same techniques can be directly applied to several other contexts.

Knowledge based approach to semantic composition of teams in an organization

Finding rapidly suitable experts in an organization to compose a team able to solve specific tasks is a typical problem in large consulting firms. In this paper we present a Description Logics approach to the semantic-based composition of ad-hoc teams based on individuals skill profiles and on task description. The selection process is carried out using a novel Concept Covering algorithm that exploits the recently proposed Concept Abduction inference service in Description Logics. The approach has been deployed as part of a skill management system that takes text files with curricula and project specifications as inputs and extracts from them available individual profiles and task descriptions, according to an ontology modeling skills.

Semantic-Based automated composition of distributed learning objects for personalized e-learning

Recent advances in e-learning techonologies and web services make realistic the idea that courseware for personalized e-learning can be built by dynamic composition of distributed learning objects, available as web-services. To be assembled in an automated way, learning objects metadata have to be exploited, associating unambiguous and semantically rich descriptions, to be used for such an automated composition. To this aim, we present a framework and algorithms for semantic-based learning objects composition, fully compliant with Semantic Web technologies. In particular our metadata refer to ontologies built on a subset of OWL-DL, and we show how novel inference services in Description Logics can be used to compose dynamically, in an approximated –but computationally tractable– way learning resources, given a requested courseware description.

Fully automated Web services orchestration in a resource retrieval scenario

We propose a framework and polynomial algorithms for semantic-based automated Web service orchestration, fully compliant with semantic Web technologies. The approach exploits the recently proposed concept abduction inference service in description logics to solve concept covering problems. We present how the proposed approach deals with not exact solutions, computing an approximate orchestration with respect to an agent request modeled using a significant subset of OWL-DL.

A semantic-based fully visual application for matchmaking and query refinement in B2C e-marketplaces

This paper presents a visual application in the framework of semantic-enabled e-marketplaces aimed at fully exploiting semantics of supply/demand descriptions in B2C and C2C e-marketplaces. Distinguishing aspects of the framework include logic-based explanation of request results, semantic ranking of matchmaking results, logic-based request refinement. The visual user interface has been designed and implemented to be immediate and simple, and it requires no knowledge of any logic principle to be fully used.

Automating competence management through non-standard reasoning

Competence management calls for automated knowledge-based services in order to take full advantage from the know-how of a company. This paper presents an integrated semantic-based knowledge management system providing decision support services for several activities typical of competence management, including core competence evaluation, human resources allocation, training programs planning. Knowledge resources are represented according to the formalism of Description Logics, which also allows for inference services crucial for the implemented solutions. We present the various features of our approach, which exploit advanced non-standard reasoning services from Description Logics, specifically developed to support knowledge management.

Knowledge elicitation for query refinement in a semantic-enabled e-marketplace

In this paper we present a knowledge-based approach to the elicitation of information from advertisements, in the framework of a semantic-enabled marketplace. The elicited information can be used for advertisements enriching and refining, without requiring users thorough knowledge of the domain, and to determine a logicbased exact match. The approach exploits non-standard inference services in Description Logics, namely Abduction and Contraction, to tackle a typical problem of semantic-enabled marketplaces, that is the difficulty the average or casual user has in exploiting all the knowledge expressed in an e-commerce domain, which appears necessary to issue requests. We present an algorithm, which returns the set of concepts not included in the request-that can be used for query refinement- and more interesting what is still missing for each available supply, to obtain an exact, bidirectional, match.

An Agency for Semantic-Based Automatic Discovery of Web-Services

With the evolution of Web service technology, services will not only become increasingly sophisticated, but also move into the area of business-to-consumer and peer-to-peer interactions. Because of todays wide variety of services offered to perform a specific task, there is a need for mediation infrastructures able to support humans or agents in the eventual selection of appropriate services. It is a common opinion that such issues should be solved adopting semantically rich unambiguous descriptions. Hence, ontologies should be used to describe services, to ease their discovery and selection. In order to perform such a selection, a matchmaking procedure, based on semantic descriptions similarity, is needed. Technologies developed for the Semantic Web based on theoretical studies on Artificial Intelligence, particularly on Description Logics, can help in this sense. As the Semantic Web is conceived as an extension of the current one, technologies developed explicitly for they both must be used synergically in order to provide a semantic layer to approaches such as UDDI registries, using OWL formatted descriptions. In this paper we present a framework for discovery of services, stored in an UDDI registry, which exposes a description whose semantic can be modeled using OWL-DL based formalism. In order to perform this task, methodologies to compute semantic differences between two descriptions and non-standard inference services have been investigated and exploited in an implemented system.

Informative Top-k Retrieval for Advanced Skill Management

The paper presents a knowledge-based framework for skills and talent management based on an advanced matchmaking between profiles of candidates and available job positions. Interestingly, informative content of top-k retrieval is enriched through semantic capabilities. The proposed approach allows to: (1) express a requested profile in terms of both hard constraints and soft ones; (2) provide a ranking function based also on qualitative attributes of a profile; (3) explain the resulting outcomes (given a job request, a motivation for the obtained score of each selected profile is provided). Top-k retrieval allows to select most promising candidates according to an ontology formalizing the domain knowledge. Such a knowledge is further exploited to provide a semantic-based explanation of missing or conflicting features in retrieved profiles. They also indicate additional profile characteristics emerging by the retrieval procedure for a further request refinement. A concrete case study followed by an exhaustive experimental campaign is reported to prove the approach effectiveness.