transcribe

Jessica Talisman: The Ontology Pipeline Knowledge Engineering Framework | Episode 57

Knowledge Graph Insights · 33m · transcribed 8d ago
More from Knowledge Graph Insights Business
𝕏 Share ▶ YouTube 📥 PDF 🤖 .md

Section Insights

# 0:00

Introduction to Knowledge Graph Insights

What is the purpose of the Knowledge Graph Insights podcast?

The podcast aims to share wisdom on knowledge graphs and semantic web technologies, making them accessible to digital and business communities.

  • The podcast is focused on demystifying knowledge graph technology.
  • It features experts sharing insights on semantic technology.
  • The mission is to democratize knowledge graph practices.
# 6:45

Dublin Core and Metadata Standards

How does the Dublin Core format contribute to metadata standards?

The Dublin Core format began with 15 core elements for basic metadata, evolving into a family of standards that help describe digital documentation and enhance interoperability.

  • Dublin Core started as a simple metadata framework.
  • It emphasizes the importance of interoperability in digital ecosystems.
  • The evolution of metadata standards supports better communication between machines and humans.
# 13:30

Framework Development in Ontology Engineering

How did Jessica Talisman develop her framework for ontology engineering?

The framework evolved from her experiences in various organizations, focusing on practical implementation and communication of ontology work to meet users' needs.

  • The framework was developed through real-world application and testing.
  • Understanding user needs is crucial for successful ontology implementation.
  • Practicality in ontology modeling is essential for organizational acceptance.
# 20:15

Challenges in Ontology Implementation

What are the key challenges organizations face when implementing ontologies?

Organizations often struggle with readiness, skill sets, and technology to support ontology systems, leading to failures in implementation and maintenance.

  • Successful ontology deployment requires organizational readiness and capability.
  • Funding and support for foundational systems are critical for sustainability.
  • Many organizations lack the necessary talent to maintain complex ontology systems.
# 27:00

Concept Graphs and Knowledge Representation

What role do concept graphs play in knowledge representation?

Concept graphs encapsulate meaning in language, enhancing the understanding and usability of ontologies and RDF systems in organizations.

  • Concept graphs are powerful tools for representing knowledge and meaning.
  • They help bridge the gap between language models and ontology usage.
  • Training and onboarding are essential for effective use of RDF and ontologies.

Transcript

0:01 This is the knowledgeraphph insights podcast episode number 57. When the idea of the semantic spectrum was introduced 25 years ago, it was meant to be a conceptual tool to help programmers and architects understand the relative benefits of different levels of semantic effort. A couple of decades later, Jessica Talisman has repurposed the model as a way to organize the actual process of developing enterprise knowledge infrastructure, which she shares in her new book, Ontology Pipeline, a framework for knowledge engineering.

0:33 >> Welcome to the knowledge graph insights podcast, where experts on knowledge graphs and the semantic web share their wisdom with the digital and business communities. Our mission is to demystify and democratize knowledge graph technology and practices to make the benefits of knowledge graphs and semantic technology accessible to all. And now here's your host, Larry Swanson. >> Hi everyone, welcome to episode number 57 of the knowledgraph insights podcast. I am super extra delighted today to welcome to the show Jessica Talisman.

1:04 Jessica, if you've been living under a rock, just in case, I will introduce her as the person. She's the owner and founder of Contextually, a knowledge graph consultancy. She's an a instructor and a curriculum designer with the knowledge graph academy with Tony Seal and Veronica Heimsbach and Katrina Carrie. she's also the author, and this is what we're going to talk about today, of the fourthcoming book ontology pipeline, a framework for knowledge engineering. so welcome, Jessica. Tell the folks a little bit more about what you're up to these days.

1:31 >> Thank you. so yes, I I am working as a consultant and so I'm working with clients and customers. also to Larry's point, teaching and developing new curriculum and new course options for knowledge graph academy soon to be released. and then my book ontology pipeline is based off of a framework I developed that was kind of a riff on the old semantic spectrum, but is a composable and decomposable way to build knowledge infrastructures. And the book will be released and available somewhere around the September 16th and 17th.

2:09 >> Excellent. Because we'll drop I'll probably drop this on either August 31st or September 1st. So folks will have a couple weeks. I'll put a link to the book in there. Well, that's interesting that I didn't know that this was originally a riff on the semantic spectrum. Are you talking about Ober's original semantic spectrum and then the subsequent >> Yeah. Talk a little bit about that. >> Yeah. So, so I felt like it was an abstraction at the time of where semantics lived, but we've always known with those of us within the semantic and knowledge engineering space have always acknowledged that there's that semantics does exist on a spectrum and when I say semantic, I mean context and meaning type of semantics where we introduce ontologies and taxonomies and these kind of knowledge artifacts, information and knowledge artifacts.

2:57 But they are varying you know you can think of it as a spectrum of of maturing structures to to be able to go from something where you're just simply giving context and meaning to all the way to introducing logic formal logic into a system. So that's where we start with controlled vocabularies. That's step one. The second step is metadata schemas which is a super important important step that's most overlooked I think then taxonomies then theory then ontologies and then knowledge graphs so it's an it's a framework that brings you through the iterative states of building a knowledge infrastructure >> yeah that's so funny I mean I knew that it paralleled that but I hadn't thought about your that that was the the riff on it because as I the thing I I really appreciate about your work is that you come out of this ancient tradition of library science and and well duh, you're going to take a language first approach and so vocabularies make a sensible starting point from that way as well.

4:00 Was that just sort of like not serendipity but just sort of like well duh that's just the way the world is. You start with vocabulary and build from there. Right. >> Well, and I think it really came out of working, you know, I started my career back in the late 1990s and it was right at that precipice when RDF was being introduced and I was working on this huge Steven Spielberg project, largest visual history catalog ever to make two to three or sorry two to six minute segments of this video available to end users and we had more than 11 and a half years of footage back to back. So if you imagine this huge catalog like how do you make these little clips? It was well before YouTube and clips discoverable.

4:42 So it was a very very early proof of concept and that at the time was based entirely on language because we had to tag content. We had to have consistency. So we essentially built a thesaurus library or librarian style that really emerged out of the library sciences and cataloging practices and and records and those sorts of things. You can think of it as the golden records. But the idea was having this consistency because where do we define meaning as humans? And that's what it really was was working towards and and thinking about how do I present something that is a repeatable process within an organization that logically makes sense that starts with humans which is how we define things.

5:32 Because ultimately when we build a knowledge infrastructure, it's about how humans define this meaning, not know the first step is not how machines define meaning. >> Yeah. No, that's God is there's so much in there. There's like a whole there's like five podcasts just in what you just said, but I'm really curious about that. when you said defining meaning in that project like 30 years ago, >> you don't have RDF, you don't have you don't have SCS, you don't you have like >> we have Dublin core. We had double core.

6:00 >> Oh, right. So you have your library tooling. Yeah. So tell me about that. >> Yeah. Tell me about well I guess maybe a quick contrast between like how you did it then just like quick overview of like how you use Dublin core for the and I assume that that was key to your metadata strategy and and everything that drove that and then like how would that unfold today? >> Oh gosh. And you know what actually that's a really good point. I would say that a lot of the practices and a lot of the core tenants of those types of systems. So using Dublin core which has you know a more mature standard for data cataloges which is called DAT and we also have DPRO which is for data products like there are these really cool W3C standards that have evolved out of the library sciences that are based on Dublin core. Dublin core is not it's it's it's it's so elegantly designed because the Dublin core format first started as 15 core elements and those core elements were like title description author like all of the basic metadata that you would want to apply to things within it with digital ecosystem.

7:08 So it was that sort of formative it doesn't declare anything as a class or property. The original thing was you just had 15 elements that could be used to describe documentation in a digital space. So that one and I think of it as a seed that one seed emerged into this whole family of standards that are used to describe things in digital ecosystems. So for example in an enterprise what we tend to do and this also comes out of the library sciences and Dublin core is we implement something and I talk about this in my book in the metadata chapter is we implement a a metadata application profile. I did this actually with Paco in sensing is bringing them through an application profile which is basically your documentation, your style guides, the rules of the road. How are we going to reconcile and it doesn't mean one one metadata schema to rule them all. It's how do we connect all of this language and meaning across an entire organization and have that meaning able to be communicated to both machines and humans. So it really speaks to interoperability.

8:21 It speaks to system design. It is speaks to the process of categorization of defining meaning of the social aspects of what so much of the industry has been trying to tackle with context and and you know we're starting to see this emergence of people now starting to think about knowledge management. How do you manage knowledge? It's very social. It's as much technical as it is social but I would say at this point it's more social than technical because it's about agreements. It's about understanding how our systems work. how definitions of meaning are translated between humans and machines.

9:00 >> Yep. Hey, one thing I want to go back double and core that goes back to like the 60s or something, right? It was like one of the >> It was the '9s. >> It was the '9s. >> Yeah. And and those original standards and it was a bunch of librarians and a few technicians that met it was actually out of Dublin, Ohio. It's less remote. >> Oh, that's where Okay. which is where the OLC is founded which is the the library or you know the organization that basically governs all library systems throughout the world.

9:30 >> But it was still quite an early is like a >> very early >> Yeah. And that's sort of like so now I want to go back to like that the Steven Spielberg project and Dublin core and like so you had Dublin core that was the the main tool that you had. How did you manage the people part of that? Like what was that? Who were you convincing to do stuff to make that project work? >> What was so interesting and I think this speaks to the ethos that a librarian brings to the table in how we architect systems is there is a core function in librarianship where you always and we hear this all the time when we build products is you always we should be building for our users. The irony is that what I've observed over 30 plus years of practice is that we tend to when we do system design, we build for each other more so than for our end users. So what we do is and and what we did then was you create functional requirements.

10:37 You cannot pass go without functional requirements where the functional requirements for the system and then you have warrant and it seems it's not like a warrant for arrest or anyone's in trouble. The idea of warrant is your users so you're building for three different warrants. One is user warrant, one is literary warrant and one is organizational warrant warrant. How does that translate? Well, the semantics the actual meaning of these things separate from the environment you're in is the literary. the organizational or the needs of the organization and the third is the user the end user like what are they trying how is this going to benefit the user. So you build functional requirements with those three different users in mind, those three different components in mind. And so we built the system to serve a function much like when we create competency questions for ontologies. What questions does the system have to answer? So it was an agreement amongst us but always keeping the end goal in mind which is how we are building a system together.

11:40 Now I will tell you that we the documentation is available online from that that original project in the thesaurus guidance but we had to we started that project it didn't work and this speaks you know the first time round we actually had to go in and rip rip out the whole insides and redesign the whole metadata and symbolic system inside of that that build. halfway through we had to go back to the drawing board because we realized that we overlook the separation of like events right of how we were architecting events. We needed events to be separate from the core metadata that was descriptive. You have administrative structural you know and descriptive metadata. So, it and I think that's a lesson learned that I I do believe is important to pull into the work in general is that your first draft, if anything, your first goround at building an ontology, of building a taxonomy, it may be horrible and you may have to go back and redesign and the second one's going to be better and the third one's going to be even better. But it's like anything you you know in learning a a new trade or a new way of thinking or doing things is that you're immersed in having a methodology towards the madness. This is not about vibe. We're not vibe coding. When you design a system, you should not be vibing that system. It's something that's intentional, that's planned, that's architected, but brings in those core components like functional requirements, who you're building this for, what does success look like, what questions do you want the system to answer?

13:19 >> And now I'm, you got me super curious now about I'm thinking of all the inputs into the evolution that led us to the current moment of ontology practice. It feels like we're fining out some stuff, some best practices, and optimal ways to do this. But yours is such an because like and you come from this library science you're working with Dublin core on this really cool very much a librarian kind of project and then so that that lessons of and now I'm just kind of picturing this vague thread from functional specs in that to like your first discovery of competency questions and how they work in an ontology engineering project to like your current and let's get into the book a little bit then like how does all this how did these prior experiences affect like how you organize the book.

14:03 >> Yeah. So I, you know, it's not like I came up with this framework out of out of thin air. It actually evolved out of coming up with this framework while flying the airplane. first in 2018, I was working at Department of Justice and I had to have a way to communicate the work and to chunk out the work while still I needed to be able to produce artifacts along the way. that engineers and different users could test that we could actually get our hands dirty with and implement and test to make sure that what we're building is working or does its job. So obviously, you know, if we go 0 to 60 and introduce ontology modeling right out of the gate, I have never had that work at an organization. It just doesn't. it's meeting the consumers, the producers, the organization where they're at.

14:58 and so after department of justice I went on to the next organization. It was overstock.com and as I was socializing this and working with the organization we won it was it was sort of like where where there was this initiative that was really interesting where and I think more organizations should do this but you created a cross team a cross this was 2019 the objective was and this was almost gified that at the organization you had to assemble a cross a cross talent team right cross functional team to come up with an initi ative that would that would that would proclaim certain objectives and deliverables that would solve a company problem or an organizational problem, right?

15:46 it. >> And so it was fun and there were prizes. And so you got to work with people you didn't normally work with, but you got to then have the engineer, the machine learning engineer, the product manager, the project manager, you know, all the SEO person and and sort of collaboratively work on something. And then basically the seauite voted based on the presentations of and ranked all of the projects of who would get the funding and they they chose the first the top three projects out of a sea of I think there were more than 30 projects that were proposed and that kind of that that's where I really codified the ontology pipeline. I wasn't calling it that then. and it was a way for me to educate while doing. It was a way for me to create artifacts while I'm building and saying, "Here's the controlled vocabulary. I cleaned this up, defined everything for you.

16:44 Here you go." And then we would test it and then we'd shape it into a taxonomy and we would take some of the learnings from the testing. And you know, back in that day at Overstock, we we were using BERT, which is a transformer model. sort of a precursor to the current LLM state we're in. So, we had a lot of fun working together on on this project. And the whole point was with a massive catalog with millions upon millions of SKUs and products, you know, and two different sites that we were working with. Can we improve findability and discoverability from both search and SEO and like all of these different avenues? and and so we had the ability to measure our successes as well.

17:27 That's and that that educate while doing that's sort of like that's it doesn't surprise me that that's how it works because that's kind of how you work now like just you're you're doing a lot of consulting work your real life work applying this stuff but you're educating like crazy writing a book. so you're you're walking the walk, walking the talk. You're educating while doing. How so that in terms of the book again like how did that like so that is that just sort of the foundation for the whole thing like hey >> that yeah exactly and and also the lessons learned where I've gone on consulting gigs or worked with other ontologists where the you know these really expert proficient talented incredibly brilliant ontologists would come into the organization and they go off into a cave and they build the ontology, but there was always the gap in meaning where the ontologist because they're sort of building based upon current data systems and and not realizing that those data systems aren't clean. They're not well defined categories like other miscellaneous like you're dealing with data systems and and and in a lot of cases metadata that's just plain missing, right? you have tables and rows and columns and cataloges that that aren't exactly well defined and and accessible to the ontologist. So I was also seeing the problem sorry I was also seeing the problem from the other direction in that we had these brilliant ontologists that would come into the project and and I would try to mitigate and bridge the gaps right so what does that look like it's you build an ontology the first one's not quite right because the definitions and the meaning of the underlying systems wasn't quite right so the one of the risks that that that exists in building ontologies is make a lot of assumptions about the underlying systems and fortunately or unfortunately I think it's one of the best things that any organization can do is actually going through by way of defining meaning within things like you know just what do these words mean what does the metadata mean what does the words in our semantic layers mean like whatever it is that then sets the foundation for a really well- constructed and truthful and honest ontology one that is actually going to do its job based upon the state of the underlying data. So the way you just described it that's like because that's the those are the stakeholders that that are of concern in this thing that like I know a lot of on well there's the kind of the top down bottom up you know middle you know different ways you can approach on ontology design but that's really interesting that as you engage ontologists in this did you have any trouble getting them on board with this sort of this the sort of semantic spectrum that you're manifesting from the vocabularies to the metadata to the taxonomies. How did Where did you meet the te the ontologists I guess?

20:23 >> Well, this is what's what's interesting is like it comes like the what it comes down to is funding enterprise funding and this is just the hard reality is that if you go and you implement an ontology like a full beautiful logical reasoning engine, right? And and you present that to the enterprise, are your systems capable? Do you have the skill sets in place? and is the rest of can can you can you reproduce what you've built elsewhere in the organization and can are there is does talent exist to maintain and build those systems. So what I have found time and time again is like when you communicate the message to your organization and you're starting to build these systems like taxonomies on top RDF systems RDFbased systems most organizations are not equipped right now. and so and and what they're funding is is that base layer that's you're meeting an organization where it's at. Now I it may sound cruel. may sound, you know, like a hard dose of reality, but the truth is if people in the organization and the talent and the technology is not quite up to speed with where you are, like you can deploy a gorgeous, beautiful ontology and knowledge graph, but but it doesn't mean anything if the enterprise cannot make sense of what you've built, right? It just doesn't. So if you want sustained funding, if you really do want to roll out a program that in and you can really leverage and get the most out of what ontologies have to offer, you have to start at that foundation.

22:00 >> I've had so many clients come to me and say, "We tried ontology, it failed because the enterprise wasn't ready or you know the the ontology broke after the ontologist ontology consultant left. We weren't able to maintain the system. We didn't know how to query it. Like there's real practical problems with >> and this must be like a factor of 10 worse now with the arrival of generative AI and all that that's entailing and both that as a just a dynamic that's driving the whole workplace, but in particular the growing need for all this talent that already doesn't exist. How do you think this seems super important?

22:41 like what's your what's your advice to executives and people who are like one helping them understand the need to fund this two to make it like sustainable not like it's not like a project it's not like a PC you're building you got to build a sustainable thing and then how do you whatever the training the recruiting all the stuff that entail is entailed in getting and building the talent >> yeah I mean it's an education first approach so I'm going through this in real time at unnamed large fortune50 organization And I will tell you that you know one most people most organizations are funding AI initiatives. That's where the money is coming from. So the first question is how is this going to improve my AI implementations truthfulness memory like any of the things that come along with ontologies. then they want the the message to you know they'll pay a large consultancy to come up with a deck that will communicate the message you know in a lot of cases at the larger companies. But the idea is that you have to lock in the messaging.

23:43 What are like what what does everyone do with this? How does everyone on the ground I'm talking about every single person from a content strategist to a data analyst like what is their role in this process? How do they contribute to this knowledge infrastructure? what are the what are the habits they need to change? what does this look like? So I'd mentioned application profile. It is a chapter in my book and I I walk through what's included in the application profile. But the idea is like give a high level and design first for things like Dublin core for DAT that are it's going to be the connective tissue across your organization. It's things like crosswalks between systems.

24:26 It's how do you reconcile language? It's like you can allow for autonomy meaning that you can have a distributed vocabulary SCOS vocabulary system but how do you match concepts across those SCOS taxonomies there's mapping relations that's a big concept for most people on the ground and for most organizations it's like oh we can have a distributed unified controlled vocabulary system with definitions in RDF you get people playing in that sandbox box and they start playing and getting tactile and working with RDF, you are going to be able to find the people naturally that are drawn to this work because they're getting to understand RDF, how to write it, how to work with it, like what that data model looks like, >> look at SCS, understand that the documentation and standards in the W3C world, which is like an entire ecosystem of the ontology standards. That is the entry point. And so that controlled vocabulary taxonomy thesaurus, you're kind of residing in that SCS v RDF vocabulary world. And I actually bought an brought bought I actually built an open-source tool available to everyone.

25:39 because it is probably one of the most important entry points is getting people understanding this ecosystem because from there what else Larry lives in RDF in the W3C ecosystem is ontology. So it's like a natural transition into that work and you're adding complexity but you understand the foundations and the fundamentals is the point. >> That's really interesting. So like this focus on vocabularies and taxonomies which is more accessible to people. They'll have done something like that somewhere. Very few proper ontologists in that cadre that you're onboarding to this. But you but this is like the the gateway drug. You you get them hooked on SC. Yeah. Without and then Yeah. That's that's a that's >> and for AI like SCOS is lighter weight and it's super powerful. Like if you imagine you have a concept with unique identifier that one unique identifier for that one concept has a preferred label alternative labels documentation properties like definitions link data like that that in and of itself drives huge value for AI and disambiguating what things mean. You can define your entire enterprise or business with that right there. and and be able to to to boost reliability, memory, certain implementations like people that are just using prompts, you know, working at one organization right now where they have a curated list of skills for Claude, right? And having like a SCS skill and helping to drive that reliability, but also having where you can choose your taxonomy skill because of the area of the organization you're in. that becomes that's a concept graph.

27:20 Like most people don't talk about concept graphs. Concept graphs are incredibly powerful because you're able to encapsulate meaning in language and we seem to forget we're working with language models. So it is incredibly powerful for that. not to mention that once you have ontologies, you can use those labels as annotations on your ontology classes and properties which gives labels to the ontology, human readable labels to the ontology. Yeah, that's again so much of this is about getting people comfortable with this because RDF is like it's it's funny to me it's like and one thing I'll just plug your course the knowledge graph academy like if you just want to get your hands dirty and write some turtle files it's a great way to do it and to see how really quite simple it is it's no you know it's just as easy as working in JSON or markdown files or whatever it's yeah but so I guess the the that ties the ties you just mentioned like counting for writing a scoff claude skill and things like that.

28:27 What else are you doing to like on board because so much of this is about so much of the funding that's being allocated now is more for like generative AI stuff are you having success in kind of like repurposing a little bit of that over towards our the the symbolic AI knowledge representation side? >> I mean like and and I think that's like you just hit on it. you're kind of sneaking that in. in terms of symbolic AI, you know that that what we're building, you build a disc taxonomy in RDF, it is symbolic AI.

28:56 it is a form of symbolic AI and and what we're all playing with and what we've been exposed to is generative AI. which is probabilistic and statistical. So, if you combine symbolic with with generative, you end up with neurosymbolic AI. And that's not a new field or domain, but it counterbalances you know the the unpredictability sometimes of statistical probability based models. that's just guessing the next word. Like the one thing we have to realize is that originally there's a long long history to to explain how we ended up where we are now. I wrote a piece on this I think about a month or two ago about the history. It's it's it's called symbolic it's it's it's basically about oh automation augmentation automation in the neuros symbolic loop. So I wrote an article about this that actually is a nice history of how we ended up where we are now. And a big part of that historically is that generative AI had always been, you know, marching towards this idea of more data equals better, you know, which went very well handinhand with the big data movement that we're kind of still in but starting to emerge from. So part of the promise of symbolic is more like we you know that it lends description and meaning and logic to the system. to help to drive reliability, to build things like memory, which are so important and people are starting to realize provenence which is really really important like attribution and provenence and and you know be able to have more resilient systems while also and it's been proven time and time again I have a bunch of research on this you know that that implementing things as simple as a thesaurus can decrease token spend by 89%.

30:54 So, with that being another concern, the the actual savings of of using a symbolic system gives, you know, makes the system more resilient, but also less expensive to operate. >> Yeah, I think the more that kind of data we can get out like, hey, does your token go a little high? We got a vocabulary that can help you with that. Hey, Jessica, I can't believe it. >> Yeah, we're we're coming up close to time, but before we wrap up, I want to make sure, is there anything last?

31:18 anything you want to revisit from the conversation or just want to make sure we share before we wrap up? >> I think it's important like the one thing is my book is meant to be if anyone remembers libraries I hope they do. is is that my book is meant to be also a reference book. It's meant to be something that people should dog ear, should bookmark, should should own, should scribble on, should, you know, go back to time and time again in that each chapter produces an artifact which you can test. And it's meant to be really a playground. you know, I have lots of really good little nuggets in there in terms of competency questions, how to build those, how to elicit knowledge when it's tacit, which I know a lot of people have been trying to figure out those practices, how to build, how do you determine how to construct your vocabularies, how do you, how do you approach leadership? Like those types of of of things are embedded within the book. So, I really built it for the practitioner and for the new person who's trying to figure out their entry point into this world of of knowledge.

32:25 >> Nice. That's so great. And as you just ring that off, I'm like any one of those could be a whole other series of podcasts, just eliciting tax knowledge on its own. so that's awesome. And I I hope everybody gets the book and just doggeears it to death. hey, but and one very last thing, Jessica, if folks want to follow you or connect online, what's the best places to find you? >> So, LinkedIn, I I have some activity there. Substack, I have a newsletter called intentional arrangement, which is the title of my second book. and knowledge graph academy of course. So if anyone's interested in learning or taking a knowledge graph course, we are going to be launching our business course, our leader leadership and business course which is a 2hour long course. So keep your eyes open for the fall for that one. But definitely order my book. feel free to reach out. I always enjoy talking to people. So >> very cool. Well, yeah, I got a glimpse at a sneak peek at it. I can definitely recommend it. Well, thank you so much, Jessica. It's always a blast to talk, but this was really fun.

33:29 >> Thank you, Larry. It's always fun talking. We'll have to follow up. >> For show notes and to sign up for our newsletter, visit our website at knowledgergraphins insights.com. And please rate and review us on your favorite podcast platform. Thank you for listening.

Summary

Jessica Talisman discusses her new book, "Ontology Pipeline," which builds upon the semantic spectrum to create a framework for developing enterprise knowledge infrastructure. The conversation emphasizes the importance of starting with controlled vocabularies and metadata schemas, and how these foundational elements can enhance knowledge management and AI implementations.

- The semantic spectrum, introduced 25 years ago, is a tool for understanding levels of semantic effort in knowledge engineering.
- Talisman's book repurposes this model into a framework for building knowledge infrastructures, emphasizing a structured approach.
- The framework advocates for starting with controlled vocabularies and metadata schemas, which are often overlooked but crucial for effective knowledge management.
- Talisman highlights the importance of user-centered design in system architecture, ensuring that systems meet the needs of end users.
- The discussion touches on the challenges of implementing ontologies in organizations, particularly when foundational data systems are not clean or well-defined.
- Talisman emphasizes the need for organizations to educate their teams about the role of knowledge infrastructure in AI initiatives.
- The book serves as a reference guide, providing practical artifacts and methodologies for practitioners in knowledge engineering.
- The conversation also explores the intersection of symbolic AI and generative AI, advocating for a balanced approach to enhance system reliability and reduce operational costs.

Questions Answered

What is the purpose of the Knowledge Graph Insights podcast?

The podcast aims to share wisdom on knowledge graphs and semantic web technologies, making them accessible to digital and business communities.

How does the Dublin Core format contribute to metadata standards?

The Dublin Core format began with 15 core elements for basic metadata, evolving into a family of standards that help describe digital documentation and enhance interoperability.

How did Jessica Talisman develop her framework for ontology engineering?

The framework evolved from her experiences in various organizations, focusing on practical implementation and communication of ontology work to meet users' needs.

What are the key challenges organizations face when implementing ontologies?

Organizations often struggle with readiness, skill sets, and technology to support ontology systems, leading to failures in implementation and maintenance.

What role do concept graphs play in knowledge representation?

Concept graphs encapsulate meaning in language, enhancing the understanding and usability of ontologies and RDF systems in organizations.

© transcribe · For agents Built with care and craft by Gokul Rajaram