arXiv subjects

Sören Auer

Publications and source records attributed to Sören Auer.

123 records · Page 7Linked to original sources

arXiv2017

Use of Knowledge Graph in Rescoring the N-Best List in Automatic Speech Recognition

With the evolution of neural network based methods, automatic speech recognition (ASR) field has been advanced to a level where building an application with speech interface is a reality. In spite of these advances, building a real-time speech recogniser faces several problems such as low recognition accuracy, domain constraint, and out-of-vocabulary words. The low recognition accuracy problem is addressed by improving the acoustic model, language model, decoder and by rescoring the N-best list at the output of the decoder. We are considering the N-best list rescoring approach to improve the recognition accuracy. Most of the methods in the literature use the grammatical, lexical, syntactic and semantic connection between the words in a recognised sentence as a feature to rescore. In this paper, we have tried to see the semantic relatedness between the words in a sentence to rescore the N-best list. Semantic relatedness is computed using TransE~\cite{bordes2013translating}, a method for low dimensional embedding of a triple in a knowledge graph. The novelty of the paper is the application of semantic web to automatic speech recognition.

cs.CL↗

arXiv2016

LITMUS: An Open Extensible Framework for Benchmarking RDF Data Management Solutions

Developments in the context of Open, Big, and Linked Data have led to an enormous growth of structured data on the Web. To keep up with the pace of efficient consumption and management of the data at this rate, many data Management solutions have been developed for specific tasks and applications. We present LITMUS, a framework for benchmarking data management solutions. LITMUS goes beyond classical storage benchmarking frameworks by allowing for analysing the performance of frameworks across query languages. In this position paper we present the conceptual architecture of LITMUS as well as the considerations that led to this architecture.

cs.PF↗

arXiv2016

Co-evolution of RDF Datasets

Linking Data initiatives have fostered the publication of large number of RDF datasets in the Linked Open Data (LOD) cloud, as well as the development of query processing infrastructures to access these data in a federated fashion. However, different experimental studies have shown that availability of LOD datasets cannot be always ensured, being RDF data replication required for envisioning reliable federated query frameworks. Albeit enhancing data availability, RDF data replication requires synchronization and conflict resolution when replicas and source datasets are allowed to change data over time, i.e., co-evolution management needs to be provided to ensure consistency. In this paper, we tackle the problem of RDF data co-evolution and devise an approach for conflict resolution during co-evolution of RDF datasets. Our proposed approach is property-oriented and allows for exploiting semantics about RDF properties during co-evolution management. The quality of our approach is empirically evaluated in different scenarios on the DBpedia-live dataset. Experimental results suggest that proposed proposed techniques have a positive impact on the quality of data in source datasets and replicas.

cs.DB↗

arXiv2016

Towards a Semantic Administrative Shell for Industry 4.0 Components

In the engineering and manufacturing domain, there is currently an atmosphere of departure to a new era of digitized production. In different regions, initiatives in these directions are known under different names, such as industrie du futur in France, industrial internet in the US or Industrie 4.0 in Germany. While the vision of digitizing production and manufacturing gained much traction lately, it is still relatively unclear how this vision can actually be implemented with concrete standards and technologies. Within the German Industry 4.0 initiative, the concept of an Administrative Shell was devised to respond to these requirements. The Administrative Shell is planned to provide a digital representation of all information being available about and from an object which can be a hardware system or a software platform. In this paper, we present an approach to developing such a digital representation based on semantic knowledge representation formalisms such as RDF, RDF Schema and OWL. We present our concept of a Semantic I4.0 Component which addresses the communication and comprehension challenges in Industry 4.0 scenarios using semantic technologies. Our approach is illustrated with a concrete example showing its benefits in a real-world use case.

cs.SE↗

arXiv2016

Git4Voc: Git-based Versioning for Collaborative Vocabulary Development

Collaborative vocabulary development in the context of data integration is the process of finding consensus between the experts of the different systems and domains. The complexity of this process is increased with the number of involved people, the variety of the systems to be integrated and the dynamics of their domain. In this paper we advocate that the realization of a powerful version control system is the heart of the problem. Driven by this idea and the success of Git in the context of software development, we investigate the applicability of Git for collaborative vocabulary development. Even though vocabulary development and software development have much more similarities than differences there are still important differences. These need to be considered within the development of a successful versioning and collaboration system for vocabulary development. Therefore, this paper starts by presenting the challenges we were faced with during the creation of vocabularies collaboratively and discusses its distinction to software development. Based on these insights we propose Git4Voc which comprises guidelines how Git can be adopted to vocabulary development. Finally, we demonstrate how Git hooks can be implemented to go beyond the plain functionality of Git by realizing vocabulary-specific features like syntactic validation and semantic diffs.

cs.AI↗

arXiv2016

Luzzu - A Framework for Linked Data Quality Assessment

With the increasing adoption and growth of the Linked Open Data cloud [9], with RDFa, Microformats and other ways of embedding data into ordinary Web pages, and with initiatives such as schema.org, the Web is currently being complemented with a Web of Data. Thus, the Web of Data shares many characteristics with the original Web of Documents, which also varies in quality. This heterogeneity makes it challenging to determine the quality of the data published on the Web and to subsequently make this information explicit to data consumers. The main contribution of this article is LUZZU, a quality assessment framework for Linked Open Data. Apart from providing quality metadata and quality problem reports that can be used for data cleaning, LUZZU is extensible: third party metrics can be easily plugged-in the framework. The framework does not rely on SPARQL endpoints, and is thus free of all the problems that come with them, such as query timeouts. Another advantage over SPARQL based qual- ity assessment frameworks is that metrics implemented in LUZZU can have more complex functionality than triple matching. Using the framework, we performed a quality assessment of a number of statistical linked datasets that are available on the LOD cloud. For this evaluation, 25 metrics from ten different dimensions were implemented.

cs.DB↗

arXiv2015

Towards Cleaning-up Open Data Portals: A Metadata Reconciliation Approach

This paper presents an approach for metadata reconciliation, curation and linking for Open Governamental Data Portals (ODPs). ODPs have been lately the standard solution for governments willing to put their public data available for the society. Portal managers use several types of metadata to organize the datasets, one of the most important ones being the tags. However, the tagging process is subject to many problems, such as synonyms, ambiguity or incoherence, among others. As our empiric analysis of ODPs shows, these issues are currently prevalent in most ODPs and effectively hinders the reuse of Open Data. In order to address these problems, we develop and implement an approach for tag reconciliation in Open Data Portals, encompassing local actions related to individual portals, and global actions for adding a semantic metadata layer above individual portals. The local part aims to enhance the quality of tags in a single portal, and the global part is meant to interlink ODPs by establishing relations between tags.

cs.IR↗

arXiv2015

Wikidata through the Eyes of DBpedia

DBpedia is one of the first and most prominent nodes of the Linked Open Data cloud. It provides structured data for more than 100 Wikipedia language editions as well as Wikimedia Commons, has a mature ontology and a stable and thorough Linked Data publishing lifecycle. Wikidata, on the other hand, has recently emerged as a user curated source for structured information which is included in Wikipedia. In this paper, we present how Wikidata is incorporated in the DBpedia ecosystem. Enriching DBpedia with structured information from Wikidata provides added value for a number of usage scenarios. We outline those scenarios and describe the structure and conversion process of the DBpediaWikidata dataset.

cs.DB↗

arXiv2015

Interest-based RDF Update Propagation

Many LOD datasets, such as DBpedia and LinkedGeoData, are voluminous and process large amounts of requests from diverse applications. Many data products and services rely on full or partial local LOD replications to ensure faster querying and processing. While such replicas enhance the flexibility of information sharing and integration infrastructures, they also introduce data duplication with all the associated undesirable consequences. Given the evolving nature of the original and authoritative datasets, to ensure consistent and up-to-date replicas frequent replacements are required at a great cost. In this paper, we introduce an approach for interest-based RDF update propagation, which propagates only interesting parts of updates from the source to the target dataset. Effectively, this enables remote applications to `subscribe' to relevant datasets and consistently reflect the necessary changes locally without the need to frequently replace the entire dataset (or a relevant subset). Our approach is based on a formal definition for graph-pattern-based interest expressions that is used to filter interesting parts of updates from the source. We implement the approach in the iRap framework and perform a comprehensive evaluation based on DBpedia Live updates, to confirm the validity and value of our approach.

cs.DC↗

arXiv2015

Luzzu Quality Metric Language -- A DSL for Linked Data Quality Assessment

The steadily growing number of linked open datasets brought about a number of reservations amongst data consumers with regard to the datasets' quality. Quality assessment requires significant effort and consideration, including the definition of data quality metrics and a process to assess datasets based on these definitions. Luzzu is a quality assessment framework for linked data that allows domain-specific metrics to be plugged in. LQML offers notations, abstractions and expressive power, focusing on the representation of quality metrics. It provides expressive power for defining sophisticated quality metrics. Its integration with Luzzu enables their efficient processing and execution and thus the comprehensive assessment of extremely large datasets in a streaming way. We also describe a novel ontology that enables the reuse, sharing and querying of such definitions. Finally, we evaluate the proposed DSL against the cognitive dimensions of notation framework.

cs.DB↗

arXiv2015

OpenCourseWare Observatory -- Does the Quality of OpenCourseWare Live up to its Promise?

A vast amount of OpenCourseWare (OCW) is meanwhile being published online to make educational content accessible to larger audiences. The awareness of such courses among users and the popularity of systems providing such courses are increasing. However, from a subjective experience, OCW is frequently cursory, outdated or non-reusable. In order to obtain a better understanding of the quality of OCW, we assess the quality in terms of fitness for use. Based on three OCW use case scenarios, we define a range of dimensions according to which the quality of courses can be measured. From the definition of each dimension a comprehensive list of quality metrics is derived. In order to obtain a representative overview of the quality of OCW, we performed a quality assessment on a set of 100 randomly selected courses obtained from 20 different OCW repositories. Based on this assessment we identify crucial areas in which OCW needs to improve in order to deliver up to its promises.

cs.CY↗

arXiv2015

"How much?" Is Not Enough - An Analysis of Open Budget Initiatives

A worldwide movement towards the publication of Open Government Data is taking place, and budget data is one of the key elements pushing this trend. Its importance is mostly related to transparency, but publishing budget data, combined with other actions, can also improve democratic participation, allow comparative analysis of governments and boost data-driven business. However, the lack of standards and common evaluation criteria still hinders the development of appropriate tools and the materialization of the appointed benefits. In this paper, we present a model to analyse government initiatives to publish budget data. We identify the main features of these initiatives with a double objective: (i) to drive a structured analysis, relating some dimensions to their possible impacts, and (ii) to derive characterization attributes to compare initiatives based on each dimension. We define use perspectives and analyse some initiatives using this model. We conclude that, in order to favour use perspectives, special attention must be given to user feedback, semantics standards and linking possibilities.

cs.CY↗

arXiv2015

Identifying Web Tables - Supporting a Neglected Type of Content on the Web

The abundance of the data in the Internet facilitates the improvement of extraction and processing tools. The trend in the open data publishing encourages the adoption of structured formats like CSV and RDF. However, there is still a plethora of unstructured data on the Web which we assume contain semantics. For this reason, we propose an approach to derive semantics from web tables which are still the most popular publishing tool on the Web. The paper also discusses methods and services of unstructured data extraction and processing as well as machine learning techniques to enhance such a workflow. The eventual result is a framework to process, publish and visualize linked open data. The software enables tables extraction from various open data sources in the HTML format and an automatic export to the RDF format making the data linked. The paper also gives the evaluation of machine learning techniques in conjunction with string similarity functions to be applied in a tables recognition task.

cs.IR↗

arXiv2015

Quality Assessment of Linked Datasets using Probabilistic Approximation

With the increasing application of Linked Open Data, assessing the quality of datasets by computing quality metrics becomes an issue of crucial importance. For large and evolving datasets, an exact, deterministic computation of the quality metrics is too time consuming or expensive. We employ probabilistic techniques such as Reservoir Sampling, Bloom Filters and Clustering Coefficient estimation for implementing a broad set of data quality metrics in an approximate but sufficiently accurate way. Our implementation is integrated in the comprehensive data quality assessment framework Luzzu. We evaluated its performance and accuracy on Linked Open Datasets of broad relevance.

cs.DB↗

arXiv2014

Representing Dataset Quality Metadata using Multi-Dimensional Views

Data quality is commonly defined as fitness for use. The problem of identifying quality of data is faced by many data consumers. Data publishers often do not have the means to identify quality problems in their data. To make the task for both stakeholders easier, we have developed the Dataset Quality Ontology (daQ). daQ is a core vocabulary for representing the results of quality benchmarking of a linked dataset. It represents quality metadata as multi-dimensional and statistical observations using the Data Cube vocabulary. Quality metadata are organised as a self-contained graph, which can, e.g., be embedded into linked open datasets. We discuss the design considerations, give examples for extending daQ by custom quality metrics, and present use cases such as analysing data versions, browsing datasets by quality, and link identification. We finally discuss how data cube visualisation tools enable data publishers and consumers to analyse better the quality of their data.

cs.DB↗