About LD Connect
Connect Data. Accelerate Research.
In collaboration with the research community, we are enriching and connecting human- and machine-readable data in more meaningful ways to contribute to an increased understanding of published research. Therefore, we present LD Connect (Linked Data Connect), which contains linked metadata from all IOS Press journals and books. It also constructs AI-powered embeddings derived from all full text, further unsiloing research data and enriching contextual relationships.
Providing machine-readable, interlinked data that are publicly available opens up a wide range of opportunities. We offer our linked data to the research and data science communities in order to stimulate new discoveries, enhance third party datasets and empower innovation. Additionally, we are working on services and semantic tools built on top of our linked data and embeddings to gain insights into how research evolves, researchers connect, institutions collaborate and more.
The portal currently contains millions of triples, i.e., individual statements and maps connections between metadata of journal articles, book chapters, authors, affiliations, keywords and other bibliographic metadata to provide a complete ecosystem of IOS Press scholarly relationships.
The unsiloing of data leads to improved retrieval, accessibility, reusability and interoperability. Structured data can be searched, shared, reused, data mined and linked to other data sources.
By enriching and fostering the interlinking of data, contextual relationships among authors, institutions and research areas can be made visible. Geocoding and spatial information add another layer of discovery.
Authors who publish their work with IOS Press are assured that their work is disseminated through both human- and machine-accessible channels following web-friendly standards.
Furthermore, downstream applications such as abstracting and indexing databases can use the data portal to ensure their own datastores are always up to date with the latest content published by IOS Press.
Additional discovery tools under development are Simple Search and the LD Connect Toolbox, which provides the means to easily unlock the relationships embedded in the data.
By freely offering our datasets in machine-readable form to third parties and semantic tools that reveal important connections, we hope to help empower the scientific research community and contribute in a meaningful way to scientific progress.
LD Connect was developed in collaboration with STKO Lab at UCSB in Santa Barbara, CA, USA and the co-reference resolution with DaSe Lab at Wright State University in Dayton, OH, USA and Kansas State University in Manhattan, KS, USA.
For insights into how the LD Connect embeddings and Toolbox were developed by the team read: Gengchen Mai, Krzysztof Janowicz, Bo Yan. Combining Text Embedding and Knowledge Graph Embedding Techniques for Academic Search Engines, In: Proceedings of SemDeep-4 Workshop co-located with ISWC 2018, Oct. 8-12, 2018, Monterey, CA, USA.