Cristina Sarasua

CrowdMap: crowdsourcing ontology alignment with microtasks

The last decade of research in ontology alignment has brought a variety of computational techniques to discover correspondences between ontologies. While the accuracy of automatic approaches has continuously improved, human contributions remain a key ingredient of the process: this input serves as a valuable source of domain knowledge that is used to train the algorithms and to validate and augment automatically computed alignments. In this paper, we introduce CrowdMap, a model to acquire such human contributions via microtask crowdsourcing. For a given pair of ontologies, CrowdMap translates the alignment problem into microtasks that address individual alignment questions, publishes the microtasks on an online labor market, and evaluates the quality of the results obtained from the crowd. We evaluated the current implementation of CrowdMap in a series of experiments using ontologies and reference alignments from the Ontology Alignment Evaluation Initiative and the crowdsourcing platform CrowdFlower. The experiments clearly demonstrated that the overall approach is feasible, and can improve the accuracy of existing ontology alignment solutions in a fast, scalable, and cost-effective manner.

Microtask Available, Send us your CV!

Most current micro task crowd sourcing platforms do not exploit the individual expertise of workers, which becomes extremely relevant for knowledge-intensive micro tasks in human computation scenarios. In this paper, we discuss work in progress on worker profiling within micro task platforms to increase both the quality of the work and the satisfaction of the users. We analyse the issue of profiling workers and propose the introduction of a crowd worker CV as a comprehensive means to describe a workers expertise and interests. We discuss several important dimensions that should be included in such a CV and analyse their benefits.

Retrieving Film Heritage Content Using an MPEG-7 Compliant Ontology

This paper presents the design and implementation of an MPEG-7 based Multimedia Retrieval System for Film Heritage. The multimedia content has been indexed using an Annotation Tool based on MPEG-7 standard. Moreover, an MPEG-7 Compliant Ontology in OWL DL, which is briefly explained in this paper, has been specially developed to fulfil the requirements of the CINeSPACE project. This ontology has been instantiated so that the retrieval process can be handled. The system has been assessed during the validation of the CINeSPACE project.

An architecture for fast semantic retrieval in the film heritage domain

How to best perform a search over a dataset is a common field of research in the scientific community. Query engines are used when the information is handled by an ontology in order to obtain structured information semantically. A common issue that arises is when the same query is performed several times, as the query engine must check the domain every time in order to retrieve the information. In this paper, we propose an architecture that takes advantage of the concept of Reflexive Ontologies (RO) in order to achieve timely semantic retrieval. The proposed architecture is illustrated by a case study in the Film Heritage domain, showing a performance improvement and providing ground for further research and discussion.

Crowd Work CV: Recognition for Micro Work

With an increasing micro-labor supply and a larger available workforce, new microtask platforms have emerged providing an extensive list of marketplaces where microtasks are offered by requesters and completed by crowd workers. The current microtask crowdsourcing infrastructure does not offer the possibility to be recognised for already accomplished and offered work in different microtask platforms. This lack of information leads to uninformed decisions in selection processes, which have been acknowledged as a promising way to improve the quality of crowd work. To overcome this limitation, we propose Crowd Work CV, an RDF-based data model that, similarly to traditional Curriculum Vitae, captures crowd workers’ interests, qualifications and work history, as well as requesters’ information. Crowd Work CV enables the representation of crowdsourcing agents’ identities and promotes their work experience across the different microtask marketplaces.

Ontology metadata for ontology reuse

Ontologies are often poorly documented, thus being hardly accessible to users and ontology reuse services. A first step towards a better ontology documentation is an explicit schema for their systematic description. To offer an informed background for such a schema we surveyed ontology engineering technology, and the types of ontology-related descriptive means they use. The result is part of the OMV standard, and was evaluated through professional reviews. A second step is the provision of automatic techniques to acquire such documentation, for which we devised the Ontology MEtadata GenerAtion (OMEGA) algorithm, presented in the second part of the paper.

Methods for intrinsic evaluation of links in the Web of Data

The current Web of Data contains a large amount of interlinked data. However, there is still a limited understanding about the quality of the links connecting entities of different and distributed data sets. Our goal is to provide a collection of indicators that help assess existing interlinking. In this paper, we present a framework for the intrinsic evaluation of RDF links, based on core principles of Web data integration and foundations of Information Retrieval. We measure the extent to which links facilitate the discovery of an extended description of entities, and the discovery of other entities in other data sets. We also measure the use of different vocabularies. We analysed links extracted from a set of data sets from the Linked Data Crawl 2014 using these measures.

Crowdsourcing and the Semantic Web (Dagstuhl Seminar 14282).

Semantic technologies provide flexible and scalable solutions to master and make sense of an increasingly vast and complex data landscape. However, while this potential has been acknowledged for various application scenarios and domains, and a number of success stories exist, it is equally clear that the development and deployment of semantic technologies will always remain reliant of human input and intervention. This is due to the very nature of some of the tasks associated with the semantic data management life cycle, which are famous for their knowledge-intensive and/or context-specific character; examples range from conceptual modeling in almost any flavor, to labeling resources (in different languages), describing their content in terms of ontological terms, or recognizing similar concepts and entities. For this reason, the Semantic Web community has always looked into applying the latest theories, methods and tools from CSCW (Computer Supported Cooperative Work), participatory design, Web 2.0, social computing, and, more recently crowdsourcing to find ways to engage with users and encourage their involvement in the execution of technical tasks. Existing approaches include the usage of wikis as semantic content authoring environments, leveraging folksonomies to create formal ontologies, but also human computation approaches such as games with a purpose or micro-tasks. This document provides a summary of the Dagstuhl Seminar 14282: Crowdsourcing and the Semantic Web, which in July 2014 brought together researchers of the emerging scientific community at the intersection of crowdsourcing and Semantic Web technologies. We collect the position statements written by the participants of seminar, which played a central role in the discussions about the evolution of our research field.

Ontology Mapping: The Case of the CINeSPACE Project

Ontology mapping is required to combine heterogeneous ontologies. Developing such ontology mapping has been a core issue of recent ontology research. This paper presents the mapping of several standard domain ontologies in order to implement the CINeSPACE integrated ontology. Four source ontologies have been selected and the set of overlapping concepts that are similar in meaning has been determined.

Assessing film heritage as a city promotion tool

Cultural tourists are currently looking for new destinations and experiences. The tourism industry itself is very competitive with many new destinations trying to attract tourists. Moreover, there has been an increasing number of tourists visiting destinations featured through films and television series which are not directly related to the tourist promotion of the Destination Management Organizations (DMO). This is a new form of tourism called Film-induced Tourism, one of the fastest growing sectors of the tourism industry. Recent research suggests that films can have strong influence on tourist decision-making and films do not only provide short-term tourism revenue but long-term prosperity to the destination. This paper investigates the way new experiences based on Information and Communication Technologies can enhance the experience of film lovers to destinations related to films such San Sebastian on the basis of the CINeSPACE project. Based on the location and profile of the user, the system delivers multimedia content that best fits his/her requirements. Results of the in situ evaluation are also provided.