News

 

UCDS lab continues to work on User-Centric Data Science with many new faces.

UCDS lab continues to work on User-Centric Data Science with many new faces. With Jacco van Ossenbruggen installed as our brand new group leader, we have been expanding the group significantly with new assistant professors, postdoc researchers and PhD students. We are now participating in multiple ICAI labs, including the Civic AI Lab and the Cultural AI Lab. We also continue to collaborate in (inter) national research projects such as Interconnect, Clariah, Hybrid Intelligence and many others. For more information, visit the People and Project pages or contact us.


 

Can a Transformer Assist in Scientific Writing?

The Semantic Web community has produced a large body of literature that is becoming increasingly difficult to manage, browse, and use. Recent work on attention-based, sequence-to-sequence Transformer neural architecture has produced language models that generate surprisingly convincing synthetic conditional text samples. In this demonstration, we re-train the GPT-2 architecture using the complete corpus of proceedings of the International Semantic Web Conference since 2002 until 2019. We use user-provided sentences to conditionally sample paper snippets, therefore illustrating cases where this model can help at addressing challenges in scientific paper writing, such as navigating extensive literature, explaining the Semantic Web core concepts, providing definitions, and even inspiring new research ideas. Links: full paper, demo poster.


 

Machine-to-machine communication in rural conditions: Realizing KasadakaNet

In his Master Project, Fahad Ali researched using wifi sneakernets for machine-to-machine communication to enable information sharing between geographically distributed devices. He developed a Raspberry Pi-based device called the Wifi-donkey that can be mounted on a vehicle and facilitates information exchange with nearby devices, using the built-in wifi card of the rPi 3.The solution is based on Piratebox offline file-sharing and communications system built with free software and uses off-the-shelf Linux software components and configuration settings to allow it to discover and connect to nearby Kasadaka devices based using Wifi technologies.


 

DIVE+ collection enrichment paper wins best paper award at MTSR2017

DIVE+ collection enrichment paper wins best paper award at the 11th Metadata and Semantics Research Conference in Tallinn, Estonia.


 

Final Release of the Big Data Europe Integrator Platform (BDI)

On Thursday 16 November, the BDE Consortium launched the third version of the Big Data Europe Integrator Platform. The technical team has set out what the Big Data Europe Integrator Platform can do, how it does it, and how you can use it to derive more value from your data.


 

Dancing and Semantics

This post describes the MSc theses of Ana-Liza Tjon-a-Pauw and Josien Jansen on the topic of Dancing and Semantics. They investigated 1) How can we model and represent dance in a sensible manner so that computers can make sense of choreographs and 2) How can we communicate those choreographies to the dancers?


 

ABC-Kb Network Institute project kickoff

Our Academy Assistant project ABC-Kb has started on "A Knowledge base supporting the Assessment of language impairment in Bilingual Children".


 

DIVE+ in Europeana Insight

This months’ edition of Europeana Insight features articles from this year’s LODLAM Challenge finalists, which include the winner: DIVE+. The online article “DIVE+: EXPLORING INTEGRATED LINKED MEDIA” discusses the DIVE+ User studies, data enrichment, exploratory interface and impact on the cultural heritage domain.


 

Data Science: a new journal

Data Science is an interdisciplinary journal that addresses the development that data has become a crucial factor for a large number and variety of scientific fields. This journal covers aspects around scientific data over the whole range from data creation, mining, discovery, curation, modeling, processing, and management to analysis, prediction, visualization, user interaction, communication, sharing, and re-use.


 

New version of SWI Prolog released

The new stable release version 7.6.0-rc has been uploaded. Please test and report issues to the mailinglist or GitHub. Some of the highlights for version 7.6 are support for mode-directed tabling, initiated by Fabrizio Riguzzi; speedup for delimited continuations and fix of the interface, which notably boosts tabling and support for multi-argument indexing, sponsored by Kyndi. For more information and a full list of changes please visit the SWI Prolog news page.