LTI

Time: 
Thursday, September 15, 2022 - 10:15 to 11:15

Talks

Multilingual Taxonomies and Knowledge Graphs as a Basis for Semantic AI Applications

The domain of taxonomies and ontologies is to structure and enrich data. This makes the data searchable, findable, usable, and, moreover, the basis for AI applications. Terminology as the "counterpart" is responsible for ensuring that both data and metadata in the company are uniform and thus reusable and linkable. We show how taxonomy and terminology together make corporate data fit for the future, and how you can build taxonomies and knowledge graphs alongside classic terminologies. We give concrete examples of how these can be implemented in practice.

Data Protection: How LT Helps Finding the Needles in the Haystack

Data protection regulation such as GDPR and the new Swiss DSG (becoming effective in 2023) forces organizations to implement suitable measures and processes to protect personal identifiable data/information (PID/PII). In particular, organizations have to be able to find all such data on a given person and to delete them if requested – or when the applicable retention period of the respective data expires.

Semi-automated Generation of Multilingual Domain-specific Taxonomies

The use of and need for domain-specific taxonomies are rapidly augmenting, as part of the growing interest in multilingual knowledge management. However, creating a fine taxonomy for any domain or industry use case can require many months of intensive expert work. To face this challenge, we converge human created and curated data with automated processes and a Knowledge Graph tool. Namely, we apply cross-lingual lexicographic content from KD-Lexicala with Semantic Web Company’s PoolParty Semantic Suite to generate multilingual domain-specific taxonomies.