Page 25 - Sirius_Annual_Report_2021

of ML models using semantic technologies [12].
Then, they investigated several practical aspects
of knowledge graph management in connection to analytics and machine learning motivated by applications from Industry 4.0 [13,14]. That is, they showed how to scale usability of ML analytics and reshape industrial knowledge graphs. Moreover, Baifan and Evgeny consoli- dated a number of research directions into an advanced SIndAIS4 project (https:/sirius-labs.no/sindais4-scaling- industrial-ai-with-semantics/) of SIRIUS that aims at Scaling Industrial AI with Semantics in four directions: human, data, methods, and applications. Within this project and together with Ahmet Soylu they selected several Bosch-funded interns – students of Ahmet – thus strengthening the Bosch-SIRIUS collaboration and disseminating it in two large Norwegian universities: NTNU and OsloMet.
Natural Language Text
RDF Data
•
Basil Ell develops approaches to align symbolic data
(i. e., ontologies) with sub-symbolic data (e. g., texts or tables). The alignment enables labeled training data to be generated via distant supervision for approaches such as information extraction (IE) for ontology population or natural language generation (NLG). Having symbolic and sub-symbolic data aligned means obtaining hybrid data that can be processed by hybrid approaches.
He received a best paper award at LDK 2021 – 3rd Conference on Language, Data and Knowledge, for his work on mining association rules that help to bridge between text and data [15] – see Figure 2. Furthermore, he develops statistical approaches that are applied
to symbolic data (KGs) for the purposes of identifying regularities and anomalies, for the prediction of missing facts, for the evaluation of the structural plausibility of facts, for bridging between structured and unstructured data (as in IE, question answering, NLG), and the structural classification of regions within graphs (which is similar to sequence labeling, but on graphs).
Natural Language Text
SPARAQL Query
Figure 2. Image from [15]. There is a non-trivial lexical gap between expressions in natural language and terms in a knowledge graph, that needs to be bridged for a couple of tasks such as Information Extraction, Question Answering, and Verbalization (of RDF data or SPARQL queries).
In 2021, we collaborated with Bosch Center for Artificial Intelligence, DNV, IBM Research, Samsung Research UK, TechnipFMC, The Alan Turing Institute, University of Lisbon, University of Malaga, and University of Oxford and we orga- nized a couple of events:
> SemTab challenge: https:/www.cs.ox.ac.uk/isg/ challenges/sem-tab/
> Ontology Matching workshop: http:/om2021.ontology matching.org/
> OAEI evaluation campaign: http:/oaei.ontology matching.org/2021/
> NeSy workshop: https:/sites.google.com/view/nesy20/ SIRIUS ANNUAL REPORT 2021 | 25