Multilinguality in Knowledge Graphs

Aus International Center for Computational Logic
Wechseln zu:Navigation, Suche

Multilinguality in Knowledge Graphs

Vortrag von Lucie-Aimée Kaffee
Abstract: In this talk, I will give an overview of my work in the domain of

multilingual knowledge graphs with a focus on Wikidata. I will speak about how well knowledge graphs are covered in terms of multilingual information, how to measure and increase their mutlilinguality, and finally about the reuse of the multilingual information. In particular, I introduce a framework to measure knowledge graphs' labels and language information for reuse in applications. Then, I will give an overview of the topic of machine translation of knowledge graph labels. Further, we explore the generation of multilingual text from triples. I will tie in my most recent work on language models with regard to multilingual and cross-cultural understanding.

The talk will take place in a hybrid fashion, physically in the APB room 3027, and online through the link:

https://bbb.tu-dresden.de/b/pio-zwt-smp-aus