Evaluating the success of vocabulary reconciliation for cultural heritage collections

Hooland, Seth van; Verborgh, Ruben; Wilde, Max De; Hercher, Johannes; Mannens, Erik; Walle, Rik Van de

doi:10.1002/asi.22763

Cited by 24 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous research provides an introduction on the topic of vocabulary reconciliation (van Hooland et al, 2013), making it possible for scholars and metadata practitioners to interconnect cultural heritage collections across the Web with the help of a browser-based graphical interface. Within this work, the content of a structured keyword field was used.…”

Section: Methodsmentioning

confidence: 99%

“…Within this work, the content of a structured keyword field was used. The current paper builds on top of this previous work, as NER allows to detect concepts in unstructured fields which can, at a later stage, be used for vocabulary reconciliation, using the methodology presented by van Hooland et al (2013). With the help of a comprehensive case study based on a freely available corpus and tools, the current paper delivers all necessary components for digital humanities scholars to repeat the analyses performed.…”

Section: Methodsmentioning

confidence: 99%

“…The majority of projects focus on lexical alignment technologies, as most of the terms can be reconciled by taking care of lemmatization, harnessing preferred labels or computing string similarity. Van Hooland et al (2013) provide a state of the art regarding the use of Linked Data for vocabulary reconciliation and illustrate how collection managers can use non-expert tools to successfully reconcile their local vocabularies with the LCSH and the AAT. By doing so, collection holders can hook up their holdings within the Linked Data cloud.…”

Section: Linked Data and The Potential Of Entity Extraction For The Dmentioning

confidence: 99%

See 2 more Smart Citations

Exploring entity recognition and disambiguation for cultural heritage collections

Hooland¹,

Wilde²,

Verborgh³

et al. 2013

Digital Scholarship in the Humanities

View full text Add to dashboard Cite

Unstructured metadata fields such as 'description' offer tremendous value for users to understand cultural heritage objects. However, this type of narrative information is of little direct use within a machine-readable context due to its unstructured nature. This paper explores the possibilities and limitations of Named-Entity Recognition (NER) and Term Extraction (TE) to mine such unstructured metadata for meaningful concepts. These concepts can be used to leverage otherwise limited searching and browsing operations, but they can also play an important role to foster Digital Humanities research. In order to catalyze experimentation with NER and TE, the paper proposes an evaluation of the performance of three third-party entity extraction services through a comprehensive case study, based on the descriptive fields of the Smithsonian Cooper-Hewitt National Design Museum in New York. In order to cover both NER and TE, we first offer a quantitative analysis of named-entities retrieved by the services in terms of precision and recall compared to a manually annotated gold-standard corpus, then complement this approach with a more qualitative assessment of relevant terms extracted. Based on the outcomes of this double analysis, the conclusions present the added value of entity extraction services, but also indicate the dangers of uncritically using NER and/or TE, and by extension Linked Data principles, within the Digital Humanities. All metadata and tools used within the paper are freely available, making it possible for researchers and practitioners to repeat the methodology. By doing so, the paper offers a significant contribution towards understanding the value of entity recognition and disambiguation for the Digital Humanities.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Linked Data and The Potential Of Entity Extraction For The Dmentioning

confidence: 99%

See 1 more Smart Citation

Exploring entity recognition and disambiguation for cultural heritage collections

Hooland¹,

Wilde²,

Verborgh³

et al. 2013

Digital Scholarship in the Humanities

View full text Add to dashboard Cite

show abstract

“…For instance, we could provide extra functionality such as substring searches [10], which enable faster evaluation of sparql queries with certain FILTER clauses. It could also drive specific tools and applications such as autocompletion widgets or linking and reconciliation tasks [8]. To improve query performance, the incorporation of additional metadata in responses can be beneficial [12].…”

Section: Discussionmentioning

confidence: 99%

dbpedia’s Triple Pattern Fragments: Usage Patterns and Insights

Verborgh

2015

The Semantic Web: ESWC 2015 Satellite Events

Self Cite

View full text Add to dashboard Cite

Abstract. Queryable Linked Data is published through several interfaces, including sparql endpoints and Linked Data documents. In October 2014, the dbpedia Association announced an official Triple Pattern Fragments interface to its popular dbpedia dataset. This interface proposes to improve the availability of live queryable data by dividing query execution between clients and servers. In this paper, we present a usage analysis between November 2014 and July 2015. In 9 months time, the interface had an average availability of 99.99%, handling 16,776,170 requests, 43.0% of which were served from cache. These numbers provide promising evidence that low-cost Triple Pattern Fragments interfaces provide a viable strategy for live applications on top of public, queryable datasets.

show abstract

“…Using Linked Open Data formats, multiple datasets can be integrated and jointly exploited by SPARQL. There have been several attempts to bring cultural heritage data into the Linked Open Data formats such as in the CultureSampo project [10] and the OpenART project [9].…”

Section: Linked Open Data: Towards An Archive For the Future?mentioning

confidence: 99%

Curios

Webster

Nguyen

Beel

et al. 2015

Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work &Amp; Social Computing

View full text Add to dashboard Cite

The CURIOS project explores how digital archives for rural community heritage groups can be made more sustainable so that volunteer members can maintain a lasting digital presence. It is developing software tools to help remote rural communities to collaboratively maintain and present information about their cultural heritage. The objective is to investigate the use of semantic web/linked data technology to build a general, flexible and "future proof" software platform that could help such projects to develop digital archives and to be sustainable over time. As an interdisciplinary project we aim to synthesise a narrative that draws from both social science and computer science perspectives by critically reflecting upon the novel approach taken and the on-going results that are being produced. Author KeywordsCultural Heritage; Digital Archives; Community heritage; Open Linked Data. ACM Classification Keywords General Terms Human Factors MOVING TOWARDS COMMUNITY DIGITAL HERITAGERural areas are characterised by a strong identity of people with place. These identities draw on a repertoire of cultural norms, knowledge, histories, customs and practices which, taken together, construct unique place identities. This cultural distinctiveness is dynamic given traditional cultural practices are reproduced and others introduced as cultural systems evolve and adapt. Forms of cultural expression, such as story-telling, music and song, poetry and literature, dance and drama, together with material objects, artifacts, sites and cultural spaces, are resources for interacting with the past and for experiencing the present. In the collection and transmission of these collections there has been a growing sense that the traditional methods for doing this are failing [13].

show abstract

Evaluating the success of vocabulary reconciliation for cultural heritage collections

Cited by 24 publications

References 20 publications

Exploring entity recognition and disambiguation for cultural heritage collections

Exploring entity recognition and disambiguation for cultural heritage collections

dbpedia’s Triple Pattern Fragments: Usage Patterns and Insights

Curios

Contact Info

Product

Resources

About