- 10th Meet-up: most probably during late Summer or early Autumn.
- 9th Meet-up: May 20th 2024 (3:30pm-6pm BST) at City, University of London, Lecture Theatre B200, University Building. Directions to get to the Lecture Theather B200.
- Registration via this form (only for in-person attendance).
- Live-stream and full recording: access link
- Agenda:
-
15:30-16:00 Coffee and Networking
-
16:00-17:00 Talk by Juan Sequeda, the Principal Scientist and Head of the AI Lab at data.world
Title: Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue! (a follow up to his talk in September).
Abstract: There is increasing evidence that question-answering (QA) systems with Large Language Models (LLMs), which employ a knowledge graph/semantic representation of an enterprise SQL database (i.e. Text-to-SPARQL), achieve higher accuracy compared to systems that answer questions directly on SQL databases (i.e. Text-to-SQL). The question remains: how can we further improve the accuracy?
Building on the observations of our previous benchmark work where the inaccurate LLM-generated SPARQL queries followed incorrect paths, we present our Ontology-based Query Check (OBQC) approach which 1) leverages the ontology of the knowledge graph to check if the LLM-generated SPARQL query matches the semantic of ontology to detect errors and 2) use the explanations of the errors with an LLM to repair the errors. Using the chat with the data benchmark, our primary finding is that our approach increases the overall accuracy to 72% including an additional 8% of unknown results. The overall error rate of 20%.
Furthermore, we will present the learnings from a series of customer hackathons on how to effectively build the knowledge graphs and set up the question answering systems.Bio: Juan Sequeda is the Principal Scientist and Head of the AI Lab at data.world. He holds a PhD in Computer Science from The University of Texas at Austin. Juan’s research and industry work has been on the intersection of data and AI, with the goal to reliably create knowledge from inscrutable data, specifically designing and building Knowledge Graph for enterprise data and metadata management. Juan is the co-author of the book “Designing and Building Enterprise Knowledge Graph” and the co-host of Catalog and Cocktails, an honest, no-bs, non-salesy data podcast.
-
17:00-18:00 Networking
-
-
3rd Symposium on Knowlkedge Graphs in the Wild (Turing AI UK Fringe event): March 25th 2024, University of Liverpool, UK. G-Flex space.
- Format: in person (around 100 participants)
- Registration and Call for pesentations and/or posters: please register here (only if you are attending in person). Deadline March 8, 2024.
- Agenda
- Invited speakers: Prof. Uli Sattler (University of Manchester) and Dr Albert Meroño Peñuela (King's College London)
- Full Fringe event details
-
2nd Symposium June 16th 2023 (10:00am-6:00pm BST), at City, University of London, Lecture Theatre C309, Tait Building. How to get to the C309 area.
- Format: in person (around 100 participants)
- Registration via City estore. Registration is now closed.
- Agenda, photos, slides, videos
-
1st Symposium: June 17th 2022 (10am-4pm BST), at the Alan Turing Institute (Enigma room).
- Format: up to 45 participants in person, broadcasted online.
- Registration via eventbrite. In person registration closes on June 3rd, 2022. Because of space constraints, maximum 2 people per organisation or group may attend in person.
- Agenda and slides.
- Photos
-
8th Meet-up: January 26th 2024 (1pm-3pm GMT)
- Format: online meetup
- Agenda
- Invited speaker: Prof. Catia Pesquita. LASIGE, Informática, Faculdade de Ciências, Universidade de Lisboa, Portugal.
- Short presentations by members
- Discussion about the group activities: AI UK Fringe Events.
- Full agenda here.
- (The talk by Prof. Chiara Ghidini has been postponed).
- Registration via this form.
- Recordings: Link to cloud recording (Passcode: kg-meetup-8). Link to public material (Google drive).
-
7th Meet-up: September 18th 2023 (2:00pm-5:30pm BST), at City, University of London, Lecture Theatre C309, Tait Building. How to get to the C309 area.
- Format: in person (and live-streamed for online participants).
- Registration via eventbrite (Select "Get tickets").
- Agenda, photos, slides, videos
-
6th Meet-up: March 3 (12pm-2pm GMT), 2023. Online. [Slides][Cloud recording (Passcode: dur01VM# )][Recording]
- Invited Speaker: Elena Simperl will talk about the Dagstuhl Seminar on Knowledge Graphs and Their Role in the Knowledge Engineering of the 21st Century [Slides] [Dagstuhl report]
- Short presentations by participants.
-
5th Meet-up: October 27 (10:30am-4pm BST), 2022. In person at the Alan Turing Institute (Enigma room).
- Participation: up to 45 (in-person) attendees and some sessions broadcasted online.
- Registration for in person attendees via eventbrite
- Fee: £5 to be given to the Oxford Health Charity (please include your name as in the eventbrite registration).
- Format: Meet-up and attending together the last sessions of the International Semantic Web Conference - ISWC (Virtual).
- Agenda and meet-up resources.
- Photos
-
4th Meet-up: April 8, 2022 (10am-12pm BST) (online)
- Keynote: Prof. Pieter Colpaert (Ghent University, Belgium). What happens before the Knowledge Graph’s querying API.
- Recordings and slides of the meet-up.
- (Due to COVID19, the original keynote by Prof. Ruben Verbough has been postponed).
-
3rd Meet-up: November 19, 2021 (online)
- Keynote: Prof. Alessandra Russo (Imperial College London). Logic-based Machine Learning: recent advancements and future directions.
- Recordings and slides of the meet-up.
-
2nd Meet-up: July 16, 2021 (online)
- Keynote: Prof. Mark Steedman (University of Edinburgh). Building and Interrogating Knowledge Graphs Using Natural Language.
- Recordings and slides of the meet-up.
-
1st Meet-up: March 15, 2021 (online)
- Keynote: Denny Vrandečić (Wikimedia Foundation). Knowledge beyond the Graph - Building a multilingual Wikipedia.
- Recordings of the meet-up.