EVENT

Talk on "Combining Large Language Models with Knowledge Graphs for Information Extraction and Retrieval-Augmented Generation" by Dr. Simon Gottschalk from L3S Research Center at the Leibniz University Hannover (Germany)

We are pleased to inform you about the upcoming seminar by Dr. Simon Gottschalk from L3S Research Center at the Leibniz University Hannover (Germany) titled : "Combining Large Language Models with Knowledge Graphs for Information Extraction and Retrieval-Augmented Generation" Everyone interested is cordially invited to attend!

Title:

Combining Large Language Models with Knowledge Graphs for Information Extraction and Retrieval-Augmented Generation

Abstract:

Large Language Models (LLMs) and Knowledge Graphs (KGs) offer complementary strengths across various areas, including text processing, knowledge representation, and fact validation. Consequently, integrating LLMs with KGs presents a significant opportunity to enhance information extraction and retrieval tasks by leveraging their combined capabilities. In this talk, I will compare LLMs and KGs, followed by presenting three distinct approaches for integrating them: (i) knowledge graph population through the extraction of Wikidata triples from Wikipedia, (ii) semantic event extraction by evaluating the performance of transformer models and LLMs in extracting event-related triples, and (iii) event collection creation using KGs and retrieval-augmented generation (RAG) applied to Web archives.

Speaker Bio:

Dr. Simon Gottschalk is a research group leader at the L3S Research Center at the Leibniz University Hannover (Germany). His research areas include knowledge graphs, spatiotemporal data predictions, web archives and large language models.

Time/Date:

15:00-16:00,Monday, October 7

Place:

NII, Room 2005 (Lecture room 1, 20F)

Contact:

If you would like to join, please contact by email.
Email :takeda[at]nii.ac.jp