Actions

ConferenceCall 2023 10 18 and ConferenceCall 2023 10 25: Difference between pages

Ontolog Forum

(Difference between pages)
 
 
Line 2: Line 2:
|-
|-
! scope="row" | Session
! scope="row" | Session
| [[session::A look across the industry, Part 1]]
| [[session::A look across the industry, Part 2]]
|-
|-
! scope="row" | Duration
! scope="row" | Duration
Line 8: Line 8:
|-
|-
! scope="row" rowspan="3" | Date/Time
! scope="row" rowspan="3" | Date/Time
| [[has date::18 Oct 2023 16:00 GMT]]
| [[has date::25 Oct 2023 16:00 GMT]]
|-
|-
| 9:00am PDT/12:00pm EDT
| 9:00am PDT/12:00pm EDT
Line 21: Line 21:


== Agenda ==
== Agenda ==
* '''Kurt Cagle''', Author of [https://thecaglereport.com/ The Cagle Report]
* '''Evren Sirin''', Stardog CTO and lead for their new [https://www.stardog.com/categories/voicebox/ Voicebox] offering
** '''Title:''' Complementary Thinking: Language Models, Ontologies and Knowledge Graphs
** '''Title:''' How Stardog Uses AI and How AI Uses Stardog
** '''Abstract:''' With the advent of Retrieval Augmented Generators (RAGs), a more or less standardized workflow has become available for integrating large language models such as ChatGPT with knowledge graphs. This in turn has raised the question about the nature of ontologies associated with LLMs and how knowledge graphs can be structured and queried to make integrated data access possible between the two types of systems. In this talk, Editor and AI Explorer Kurt Cagle of The Cagle Report looks at this process and discusses how they affect both knowledge portals and ontology design.
** '''Abstract:''' Stardog’s AI strategy can be summarized as hybrid, applied, in-house, and user-focused. "Hybrid" derives from understanding that data management systems should provide crisp, provably correct, trusted answers to questions, but also benefits from considering fuzzy, not-terribly-wrong answers. "Applied and in-house" is focused on using foundational LLMs, NLP, or AI infrastructures to address the challenges of data modeling, data mapping, query generation, rule creation and more. "User-focused" pivots around capabilities such as question answering without any need to write queries, using ordinary language to manage a data lifecycle, and semi-supervised integration of an enterprise's structured, semi-structured, and unstructured data. The overall goal is universal self-service analytics. A significant step towards the goal is Stardog's [https://www.stardog.com/categories/voicebox/ Voicebox] which leverages LLM to build, manage, and query knowledge graphs using ordinary language.
** [https://bit.ly/3S040lR Slides]
* '''Yuan He''', Key contributor to [https://krr-oxford.github.io/DeepOnto/ DeepOnto], a package for ontology engineering with deep learning
* '''Tony Seale''', Knowledge graph architect and thought leader ([https://www.linkedin.com/in/tonyseale/ LinkedIn])
** '''Title:''' DeepOnto: A Python Package for Ontology Engineering with Deep Learning and Language Models
** '''Title:''' How Ontologies Can Unlock the Potential of Large Language Models for Business
** '''Abstract:''' Integrating deep learning techniques, particularly language models (LMs), with knowledge representations like ontologies has raised widespread attention, urging the need for a platform that supports both paradigms. However, deep learning frameworks like PyTorch and Tensorflow are predominantly developed for Python programming, while widely-used ontology APIs, such as the OWL API and Jena, are primarily Java-based. To facilitate seamless integration of these frameworks and APIs, we present [https://krr-oxford.github.io/DeepOnto/ DeepOnto], a Python package designed for ontology engineering with deep learning. The package encompasses a core ontology processing module founded on the widely-recognized and reliable OWL API, encapsulating its fundamental features in a more “Pythonic” manner and extending its capabilities to incorporate other essential components including reasoning, verbalization, normalization, projection, taxonomy, and more. Building on this module, DeepOnto offers a suite of tools, resources, and algorithms that support various ontology engineering tasks, such as ontology alignment and completion, by harnessing deep learning methods, primarily pre-trained LMs.
** '''Abstract:''' LLMs have remarkable capabilities; they can craft letters, analyze data, orchestrate workflows, generate code, and much more. Companies such as Google, Apple, Amazon, Meta, and Microsoft are all investing heavily in this technology. Everything indicates that LLMs have enormous disruptive potential. However, there is a problem: they can hallucinate, and for any serious business, that is a deal-breaker. This is where ontologies can come in. In combination with Knowledge Graphs, they can place guardrails around the LLMs, thus allowing organizations to harness the capabilities of LLMs within the framework of a safely controlled ontological structure. 
 
[https://bit.ly/46A3EH2 Slides]
 
[https://bit.ly/46DJyvo Video Recording]


== Conference Call Information ==
== Conference Call Information ==
* Date: '''Wednesday, 18 October 2023'''  
* Date: '''Wednesday, 25 October 2023'''  
* Start Time: 9:00am PDT / 12:00pm EDT / 6:00pm CEST / 5:00pm BST / 1600 UTC
* Start Time: 9:00am PDT / 12:00pm EDT / 6:00pm CEST / 5:00pm BST / 1600 UTC
** ref: [http://www.timeanddate.com/worldclock/fixedtime.html?month=10&day=18&year=2023&hour=12&min=00&sec=0&p1=179 World Clock]
** ref: [http://www.timeanddate.com/worldclock/fixedtime.html?month=10&day=25&year=2023&hour=12&min=00&sec=0&p1=179 World Clock]
* Expected Call Duration: 1 hour
* Expected Call Duration: 1 hour
{{:OntologySummit2024/ConferenceCallInformation}}
{{:OntologySummit2024/ConferenceCallInformation}}
Line 45: Line 40:


== Resources ==
== Resources ==
* [https://bit.ly/46DJyvo Video Recording]


== Previous Meetings ==
== Previous Meetings ==
{{#ask: [[Category:OntologySummit2024]] [[Category:Icom_conf_Conference]] [[<<ConferenceCall_2023_10_18]]
{{#ask: [[Category:OntologySummit2024]] [[Category:Icom_conf_Conference]] [[<<ConferenceCall_2023_10_25]]
         |?|?Session|mainlabel=-|order=desc|limit=3}}
         |?|?Session|mainlabel=-|order=desc|limit=3}}
== Next Meetings ==
== Next Meetings ==
{{#ask: [[Category:OntologySummit2024]] [[Category:Icom_conf_Conference]] [[>>ConferenceCall_2023_10_18]]
{{#ask: [[Category:OntologySummit2024]] [[Category:Icom_conf_Conference]] [[>>ConferenceCall_2023_10_25]]
         |?|?Session|mainlabel=-|order=asc|limit=3}}
         |?|?Session|mainlabel=-|order=asc|limit=3}}


Revision as of 18:03, 22 October 2023

Session A look across the industry, Part 2
Duration 1 hour
Date/Time 25 Oct 2023 16:00 GMT
9:00am PDT/12:00pm EDT
4:00pm GMT/5:00pm CST
Convener Andrea Westerinen and Mike Bennett

Ontology Summit 2024 A look across the industry, Part 2

Agenda

  • Evren Sirin, Stardog CTO and lead for their new Voicebox offering
    • Title: How Stardog Uses AI and How AI Uses Stardog
    • Abstract: Stardog’s AI strategy can be summarized as hybrid, applied, in-house, and user-focused. "Hybrid" derives from understanding that data management systems should provide crisp, provably correct, trusted answers to questions, but also benefits from considering fuzzy, not-terribly-wrong answers. "Applied and in-house" is focused on using foundational LLMs, NLP, or AI infrastructures to address the challenges of data modeling, data mapping, query generation, rule creation and more. "User-focused" pivots around capabilities such as question answering without any need to write queries, using ordinary language to manage a data lifecycle, and semi-supervised integration of an enterprise's structured, semi-structured, and unstructured data. The overall goal is universal self-service analytics. A significant step towards the goal is Stardog's Voicebox which leverages LLM to build, manage, and query knowledge graphs using ordinary language.
  • Yuan He, Key contributor to DeepOnto, a package for ontology engineering with deep learning
    • Title: DeepOnto: A Python Package for Ontology Engineering with Deep Learning and Language Models
    • Abstract: Integrating deep learning techniques, particularly language models (LMs), with knowledge representations like ontologies has raised widespread attention, urging the need for a platform that supports both paradigms. However, deep learning frameworks like PyTorch and Tensorflow are predominantly developed for Python programming, while widely-used ontology APIs, such as the OWL API and Jena, are primarily Java-based. To facilitate seamless integration of these frameworks and APIs, we present DeepOnto, a Python package designed for ontology engineering with deep learning. The package encompasses a core ontology processing module founded on the widely-recognized and reliable OWL API, encapsulating its fundamental features in a more “Pythonic” manner and extending its capabilities to incorporate other essential components including reasoning, verbalization, normalization, projection, taxonomy, and more. Building on this module, DeepOnto offers a suite of tools, resources, and algorithms that support various ontology engineering tasks, such as ontology alignment and completion, by harnessing deep learning methods, primarily pre-trained LMs.

Conference Call Information

  • Date: Wednesday, 25 October 2023
  • Start Time: 9:00am PDT / 12:00pm EDT / 6:00pm CEST / 5:00pm BST / 1600 UTC
  • Expected Call Duration: 1 hour
  • Video Conference URL: https://bit.ly/48lM0Ik
    • Conference ID: 876 3045 3240
    • Passcode: 464312

The unabbreviated URL is: https://us02web.zoom.us/j/87630453240?pwd=YVYvZHRpelVqSkM5QlJ4aGJrbmZzQT09

Participants

Discussion

Resources

Previous Meetings

 Session
ConferenceCall 2023 10 18A look across the industry, Part 1
ConferenceCall 2023 10 11Setting the stage
ConferenceCall 2023 10 04Overview

Next Meetings

 Session
ConferenceCall 2023 11 01Demos of information extraction via hybrid systems
ConferenceCall 2023 11 08Broader thoughts
ConferenceCall 2023 11 15Synthesis
... further results
Retrieved from "https://ontologforum.com/index.php?title=ConferenceCall_2023_10_18&oldid=4745"