8–9 Sept 2026
Europe/Berlin timezone

You ask iAnswer: Mobilizing iDiv Data for the Public with a Question-Answering Interface for the PhenObs Knowledge Graph

Not scheduled
20m
Talk Open Session

Speaker

Tarek Al Mustafa (iDiv)

Description

iDiv has amassed heaps of knowledge – hidden in publications, theses, and databases. In the iAnswer project we want to explore whether a combination of Large Language Models (LLMs) and Knowledge Graphs (KGs) can unveil this knowledge and make it accessible to scientists and the general public. In the first year of iAnswer, we collaborated with the team of the iDiv strategic project PhenObs to build a semantically enriched KG for PhenObs data that represents phenological observations and integrates species and botanical garden information with LCVP, GBIF, and Wikidata to further support data synthesis efforts. As KG querying is notoriously difficult for non-expert users, we developed a user interface application that allows queries via natural language with the help of LLM techniques. With this application, we support users of different levels of ecological expertise to interact with research data by translating query results into language appropriate for different user groups. In this talk, we present our efforts and lessons learned to the iDiv community and give an outlook on our plans for the next two years of iAnswer.

Status Group Doctoral Researcher
FOR TALKS: Poster Presentation Option No, I prefer to present only as a talk.

Author

Co-authors

Prof. Birgitta König-Ries (iDiv, Uni Jena) Prof. Christian Wirth (iDiv, Uni Leipzig) Robert Rauschkolb Dr Steffen Neumann (iDiv, IPB Halle)

Presentation materials

There are no materials yet.