%0 Journal Article %1 AlexievNikolova2019-EHRI-UmanisticaDigitale %A Alexiev, Vladimir %A Nikolova, Ivelina %A Hateva, Neli %D 2019 %E Brazzo, Laura %E Rodriguez, Kepa J. %I Associazione per l'Informatica Umanistica e la Cultural Digitale, Universita di Bologna (AIUCD) %J Umanistica Digitale %K EAD EHRI Geonames Holocaust_research OAI_PMH ResourceSync VIAF VRE Wikidata access_points archives authorities coreferencing deduplication digital_humanities person_matching record_linking research_infrastructure semantic_archive_integration semantic_integration thesauri %N 4 %R 10.6092/issn.2532-8816/9049 %T Semantic Archive Integration for Holocaust Research: the EHRI Research Infrastructure %U https://umanisticadigitale.unibo.it/article/view/9049 %X The European Holocaust Research Infrastructure (EHRI) is a large-scale EU project that involves 23 institutions and archives working on Holocaust studies, from Europe, Israel and the US. In its first phase (2011-2015) it aggregated archival descriptions and materials on a large scale and built a Virtual Research Environment (portal) for Holocaust researchers based on a graph database. In its second phase (2015-2019), EHRI2 seeks to enhance the gathered materials using semantic approaches: enrichment, coreferencing, interlinking. Semantic integration involves four of the 14 EHRI2 work packages and helps integrate databases, free text, and metadata to interconnect historical entities (people, organizations, places, historic events) and create networks. We will present some of the EHRI2 technical work, including critical issues we have encountered. WP10 (EAD) converts archival descriptions from various formats to standard EAD XML; transports EADs using OAI PMH or ResourceSync; ingests EADs to the EHRI database; enables use cases such as synchronization; coreferencing of textual Access Points to proper thesaurus references. WP11 (Authorities and Standards) consolidates and enlarges the EHRI authorities to render the indexing and retrieval of information more effective. It addresses Access Points in ingested EADs (normalization of Unicode, spelling, punctuation; deduplication; clustering; coreferencing to authority control), Subjects (deployment of a Thesaurus Management System in support of the EHRI Thesaurus Editorial Board), Places (coreferencing to Geonames); Camps and Ghettos (integrating data with Wikidata); Persons, Corporate Bodies (using USHMM HSV and VIAF); semantic (conceptual) search including hierarchical query expansion; interconnectivity of archival descriptions; permanent URLs; metadata quality; EAD RelaxNG and Schematron schemas and validation, etc. WP13 (Data Infrastructures) builds up domain knowledge bases from institutional databases by using deduplication, semantic data integration, semantic text analysis. It provides the foundation for research use cases on Jewish Social Networks and their impact on the chance of survival. WP14 (Digital Historiography Research) works on semantic text analysis (semantic enrichment), text similarity (e.g. clustering based on Neural Networks, LDA, etc), geo-mapping. It develops Digital Historiography researcher tools, including Prosopographical approaches.

@article{AlexievNikolova2019-EHRI-UmanisticaDigitale, abstract = {The European Holocaust Research Infrastructure (EHRI) is a large-scale EU project that involves 23 institutions and archives working on Holocaust studies, from Europe, Israel and the US. In its first phase (2011-2015) it aggregated archival descriptions and materials on a large scale and built a Virtual Research Environment (portal) for Holocaust researchers based on a graph database. In its second phase (2015-2019), EHRI2 seeks to enhance the gathered materials using semantic approaches: enrichment, coreferencing, interlinking. Semantic integration involves four of the 14 EHRI2 work packages and helps integrate databases, free text, and metadata to interconnect historical entities (people, organizations, places, historic events) and create networks. We will present some of the EHRI2 technical work, including critical issues we have encountered. WP10 (EAD) converts archival descriptions from various formats to standard EAD XML; transports EADs using OAI PMH or ResourceSync; ingests EADs to the EHRI database; enables use cases such as synchronization; coreferencing of textual Access Points to proper thesaurus references. WP11 (Authorities and Standards) consolidates and enlarges the EHRI authorities to render the indexing and retrieval of information more effective. It addresses Access Points in ingested EADs (normalization of Unicode, spelling, punctuation; deduplication; clustering; coreferencing to authority control), Subjects (deployment of a Thesaurus Management System in support of the EHRI Thesaurus Editorial Board), Places (coreferencing to Geonames); Camps and Ghettos (integrating data with Wikidata); Persons, Corporate Bodies (using USHMM HSV and VIAF); semantic (conceptual) search including hierarchical query expansion; interconnectivity of archival descriptions; permanent URLs; metadata quality; EAD RelaxNG and Schematron schemas and validation, etc. WP13 (Data Infrastructures) builds up domain knowledge bases from institutional databases by using deduplication, semantic data integration, semantic text analysis. It provides the foundation for research use cases on Jewish Social Networks and their impact on the chance of survival. WP14 (Digital Historiography Research) works on semantic text analysis (semantic enrichment), text similarity (e.g. clustering based on Neural Networks, LDA, etc), geo-mapping. It develops Digital Historiography researcher tools, including Prosopographical approaches.}, added-at = {2021-08-25T16:07:36.000+0200}, author = {Alexiev, Vladimir and Nikolova, Ivelina and Hateva, Neli}, biburl = {https://www.bibsonomy.org/bibtex/2098a39ace43ed29e55d0803dba7bb76e/valexiev}, categories = {Arts and humanities, Digital libraries and archives, Information retrieval, Web searching and information discovery, Document searching, Document metadata, Semantic web description languages, Ontologies, Thesauri}, doi = {10.6092/issn.2532-8816/9049}, editor = {Brazzo, Laura and Rodriguez, Kepa J.}, interhash = {abe772344e443e231d357198718fc52d}, intrahash = {098a39ace43ed29e55d0803dba7bb76e}, journal = {Umanistica Digitale}, keywords = {EAD EHRI Geonames Holocaust_research OAI_PMH ResourceSync VIAF VRE Wikidata access_points archives authorities coreferencing deduplication digital_humanities person_matching record_linking research_infrastructure semantic_archive_integration semantic_integration thesauri}, month = mar, number = 4, publisher = {Associazione per l'Informatica Umanistica e la Cultural Digitale, Universita di Bologna (AIUCD)}, timestamp = {2021-08-25T16:07:36.000+0200}, title = {Semantic Archive Integration for Holocaust Research: the EHRI Research Infrastructure}, url = {https://umanisticadigitale.unibo.it/article/view/9049}, url_pdf = {http://rawgit2.com/VladimirAlexiev/my/master/pubs/AlexievNikolova2018-Semantic-Archive-Integration.pdf}, year = 2019 }