Taxonomy Boot Camp London 2026

I was thrilled to participate in the Taxonomy Boot Camp London conference, which was in-person in London this past month for the first time since 2019. A sister conference to Taxonomy Boot Camp in the United States, which has been running since 2005, Taxonomy Boot Camp London had been running “Bite- Sized” online editions of half a day three times per years since 2020, which had been so successful that they continued through last year. The online edition will continue now, once a year, scheduled next for October 7.

Taxonomy Boot Camp London continues to be successfully chaired by London-based taxonomy consultant Helen Lippell, since its first year. She summarized this year’s conference: “I pushed the boundaries of my own knowledge and got to see a huge range of talks by our wonderful speakers …. Our workshops gave attendees the perfect grounding in foundational concepts too.”

As taxonomies are a niche specialty, which are applied to other related fields, the Taxonomy Boot Camp conference is always combined (co-located) with other conferences operated by Information Today Inc. In the United States, this has always been with KMWorld (knowledge management) and additional co-located conferences. For Taxonomy Boot Camp London, from 2016 to 2019 the conference had been co-located with Internet Librarian International to bring in enough attendance to make use of the venue and catering, but the conferences were not similar enough in content or attendance, and did not share keynotes, exhibits, or breaks. This year, for the first time, a new conference of KMWorld Europe was launched, and Taxonomy Boot Camp was fully combined with it, sharing keynotes, meals and breaks, exhibit space, and registration options. This made a lot more sense, due to the overlap of taxonomies and knowledge management. Personally, I also enjoyed seeing knowledge management colleagues, in addition to taxonomy colleagues, at the conference.

Conference Sessions

The format of the conference was the same as in previous years. After a shared keynotes each day, the conference is run in two tracks each day. Tracks are not the same as Taxonomy Boot Camp (Washington, DC (Beginner and case studies, and in two tracks only the first day) but rather on loose themes, which this year were “Components of Successful Semantic Projects”; “Joining Up Data With Semantics;” “Getting the Most of Curating Content, Data, and AI”; and “Taking Structure to the Next Level.” It was difficult to decide what to attend, and I moved between tracks often. 

Taxonomy Boot Camp London differs from Taxonomy Boot Camp (DC) by including preconference workshop options on the afternoon before the main conference. There were four workshops to choose from in the single time slot, two for Taxonomy Boot Camp, and two for KMWorld. “Taxonomy Design Fundamentals,” which I taught, and “Finding a Forever Home: Governance, Ownership, & the Long-Term Care of Taxonomies” were the two taxonomy workshops. 

The keynote speakers, Ben Clinch on the first day and Noz Urbina on the second day, both were excellent in taking up different angles to the topic of AI in knowledge management, while also touching on taxonomy.

What was interesting about the conference sessions was the diversity of presentation subjects. While some provided the expected information on how to create good taxonomies (including my joint presentation with Joseph Busch on Thesaurus Standards for Taxonomies”) and others were case study applications of taxonomies, there were additional, different topics. Bob Kasenchak of Factor presented an interesting perspective of semantic layers as abstraction layers, Teodora Petkova of Graphwise presented on how to embed meaning and consistency in content to support knowledge graphs and shared understanding. Craig Johnson of Xemma presented on how research was done to obtain taxonomist-user input in designing a new taxonomy management system.

Connecting to other knowledge organization systems was a common topic, with presentations on the connections of taxonomies and ontologies by Steve McComb of Semantic Arts and Paul Appleby and Ravinder Singh both of Graphifi, the intersection of taxonomies and terminologies by Jo Chapman, and taxonomies as metadata by Yonah Levenson.

There were, of course, numerous sessions on AI use in taxonomy building. Ahren Lehnart spoke about the ways to identify the best concepts out of those being suggested by machine learning and LLMs.  Panos Mitzias of Squirro presented on how AI can help accelerate tasks like concept discovery, drafting structures, and enriching taxonomies, but success still depends on clear scoping, stakeholder engagement, and ongoing governance. Fran Alexander of Expedia presented on various considerations regarding the use of LLMs in taxonomy creation including, provenance, traceability, authoritativeness, context, and the use of multiple LLM agents. Fran, Bob, Kasenchak, and Stephanie Lemieux came together for an impromptu panel discussion on the use of AI in taxonomy creation (filling in for a cancelled speaker). They spoke on the various positive uses of AI and the ways in which AI was still not so good. I found this panel most interesting, so I decided to submit such a panel topic for Taxonomy Boot Camp in Washington, DC, this November

Sessions are not recorded, but most of the slides are available on the conference website. Ahren Lehnart also blogged on the conference themes. 

Conference Details

The joint conferences had a total of about 250 attendees, which compares with 170 for Taxonomy Boot Camp London only in the prior years. (It’s not possible to break out Taxonomy Boot Camp registrants only, since many chose a “all access pass” to both conferences.)  The international aspect was great, with representatives from 29 countries. 

For the first time, the London conference (Taxonomy Boot Camp and KMWorld jointly) had a nearby off-site networking drinks reception the evening after the workshops and before the main conference. The semi-enclosed rooftop bar was a great place to meet and mingle. 

The conference facility venue location was better than previous years, being in central London, close to the Tower of London. The only issue is that the conference organizers were not sure how many attendees to expect, so they were conservative with the space, which turned out a little tight. Although there was enough seating the conference session rooms (barely), the showcase area, which was also where breakfast, lunch, and break refreshments were served, became quite crowded at times. So, it was challenging sometimes to meet people and visit all the exhibitors at times.

The vendor showcase was larger, and had better dedicated space, compared to the former Taxonomy Boot Camp London in-person events. I recall the 2-3 vendors back then having tables just outside the conference room doors. The dedicated showcase space where breakfast lunch and coffee breaks were served was a benefit for the exhibitors. As the venue was in the basement level, excavated ancient Roman walls were on display behind the exhibits. More taxonomy/ontology software vendors were present than in the past: Graphwise (formerly PoolParty), Squirro (vendor of Synaptica), Graphifi (vendor of Graphologi), and a brand new entrant Xemma. The taxonomy/ontology vendors were mixed in with the knowledge management vendors without distinction, and it was good to have this cross-over to learn more about what is available.

Taxonomy Boot Camp in London and the United States

The scope of subjects and themes of Taxonomy Boot Camp London are the same as at Taxonomy Boot Camp in the United States, but the many of the presenters are different with different case studies and stories to tell, and those presenters who are the same (like myself) do not give the same presentations at both conferences. The attendees (delegates) are also different. So, if you're just getting started with taxonomies, either Taxonomy Boot Camp London, or Taxonomy Boon Camp in Washington, DC, whichever is more convenient, is appropriate. If taxonomies are your profession, then you should try to attend each conference at least once. It’s worth the trip. I am looking forward to Taxonomy Boot Camp London / KMWorld Europe next time in April 2027.

Helen Lippell reflected: “I thoroughly enjoyed seeing the event come to fruition after all the hard work the team put in over the last year, and one of my abiding memories will be walking around after the last sessions seeing everyone just chatting away while the venue staff tried to tidy up! I take this as a sign of our community being in rude health and ready to grow in future years.”

 

 

 

Semantic Data Conference 2025

This week I attended the second annual conference “SemanticData: Taxonomy, Ontology, and Knowledge Graphs,” hosted by Henry Stewart (HS) Events and co-located with the HS DAM (Digital Asset Management) conference. I found this conference to be very worthwhile to attend, even without presenting, for its networking opportunities and ideas shared. As a one-day one-track-only conference, it had only 12 speakers, so I was not a speaker again this year, as I was last year, in order to let others speak.

Ideas of Semantics

Semantic data means enriching data with meaning from controlled vocabularies, especially taxonomies, and with meaningful relationships and specific attributes, provided by ontologies. Taxonomies and ontologies are referred to then as “semantic models.” A knowledge graph is a semantic model plus all of the connected data, which is stored in a graph database.

How “semantics” was discussed was up to each speaker. Jessica Talisman gave an overview of semantic models in what she describes as the "semantic pipeline.” In his talk on information ethics, Gary Carlson stayed high-level, stating “Semantics is about moving information from one place to another.” By contrast, Ashleigh Faith focused on the practical application of semantic tags to benefit AI. In his keynote, Ahren Lehnart spoke of the need to trust semantic models and concluded by focusing on the people, listing what “semantic professionals” do, including driving semantic adoptions within an organization, engaging with subject matter experts, seeking out and staying involved in AI projects, targeting high-risk semantic cases, and designing transparency into semantic models.

Turning to practice, Melissa Knudtson Monsalve explained the adoption of “just enough semantics” as a solution for organizations facing challenges of implementing semantic models. The conference also had some interesting case studies. Laura Rodriguez spoke about taxonomy governance strategies undertaken at HealthStream. Tracy Forzaglia explained the use of taxonomy and tagging at Scholastic. Mindy Carner explained the implementation of the DITA structured content standard in conjunction with a controlled vocabulary to manage and deliver Help Center content at LinkedIn. Finally, Dr. Robert Sanderson explained and demonstrated Yale’s LUX Collections Discovery utilizing a cultural heritage ontology and knowledge graph.

Comparisons with Semantic Data 2024

I had blogged about the first conference, Semantic Data 2024, last year. The format was the same: Individual half-hour presentations, the first as a “keynote”, a participant discussion activity, and a panel discussion moderated by the chair. By comparison, the conference was larger this year, up from about 50 attendees to about 70, making the room quite full. Aside from the chair and two of the sponsors, all but one of the speakers were also different this year from last. 

Madi Weland Solomon was again the conference chair and moderator, and Factor and Datavid were again sponsors with sponsored talks that were not promotional. Gary Carlson of Factor presented on the importance of data quality in semantic architecture, and Tim Padilla of Datavid presented on the AI-readiness of enterprise data. Progress Software was a new sponsor, but instead of a sponsored talk, Jim Morris of Progress spoke on the closing panel.

Panel: Solomon, Morris, Sanderson, and Faith

The theme of AI (especially generative AI and LLMs) was somewhat more prominent in the conference this year, taken up in almost half of the sessions. Ashleigh Faith’s talk, “How Semantic Tags Benefit AI,” was especially practical and informative. AI was woven through Ahren Lehnart’s opening keynote, when he discussed semantic trends and predictions. Tracy Forzaglia’s case study was about tagging with AI. Finally, the closing panel discussion had a focus on AI this time even in its title “Semantic Architects vs. AI: Who Curates the Future?” In fact, the conference could be title: “Semantic Data: Taxonomy, Ontology, Knowledge Graphs, and AI.” The importance of “human in the loop” with regard to AI and semantic automation was emphasized.

The “roundtable” group discussion members addressed questions of their organization’s semantic maturity, important changes in the past year, and what topics they would like to have addressed next year. This proved to be a popular session, although the large number of attendees required more time than allotted, and the room did not have tables. Perhaps a larger room or two tracks will be needed next year. I hope to participate next fall, if my schedule allows. Meanwhile, those of you in Europe may attend Semantic Data Europe on June 25, 2026, in London.

 

Talking about Taxonomies in India

I was thrilled to bring together my passions of my taxonomy profession, connecting with people, and international travel on my visit to India this month, my first time to this fascinating country.

I travel to speak about taxonomies at conferences and other events. I like to travel: to meet colleagues in this specialized field, in which I don’t have regular in-person interactions, and to see and learn about new places. Usually for me business travel is the primary purpose and seeing new places (museums or a walking tour of parts of a city) is secondary. However, for January 2025, I decided to choose a new country destination, India, primarily as a tourist, and then to add on some professional events.

Why visit India

India is now the most populous country of the world, and I have met many Indians living and working in the U.S. and in Europe, especially in technology roles. So, I wanted to understand the country and culture better. India also has a long rich history and impressive historical structures to visit, tasty food, and different religions and traditions to learn about.

I have many professional connections in India, especially through LinkedIn, more than any other country outside North America and Europe. A few are taxonomists, some have taken my course, some have bought my book, and many have a significant number of shared contacts in my field. I had also made contacts through conferences.

Finally, the use of the English language in professional activities makes it easier for me to participate in events in India: giving presentations and listening to the presentations of others. I cannot simply give a presentation in English in any country.

Multiple presentations and meetings

Taxonomies are relevant to multiple disciplines: library and information science, content and document management, information architecture, knowledge management, and ontologies. To interact with professionals in these different fields, I had to arrange multiple presentations or meetups.

Library and information science students

I have occasionally been asked to give guest lectures on about taxonomies to library/information science school classes. Close to two years ago, a graduate student of library and information science in Bengaluru (Bangalore), Soumyakanta Barik, who had read my book, asked if I would give a guest lecture (remote) to his class of master’s degree students, which I did. Afterwards informed Soumyakanta that I was thinking of coming to India, so perhaps I might present again in person. Even though Soumyakanta had since graduated, he facilitated the contacts to make such a lecture possible, so I gave an update of my prior presentation “Tidbits of Taxonomies.”

It turned out that this school of library and information science, the Documentation Research and Training Centre at the Indian Statistical Institute, Bangalore, had been founded by Dr. S. R. Ranganathan, the developer of the first major faceted classification system in the world (whom I mention in my book and in a prior blog post on faceted classification) and the father of library science in India.

Taxonomists and ontologists

On LinkedIn, I had over 25 connections with the keyword “taxonomy” and 15 with “ontology” in their profiles located in Bengaluru India, so I didn’t want to limit my presentation in that city to just current students. At my request, the Documentation Research and Training Centre organized a second presentation for me to give later the same day to be open to the public. I presented on a slightly more advanced topic, “From Taxonomy to Ontology,” based on a recent presentation that I gave at the Henry Stewart Semantic Data conference. Although the day I chose to present turned out to be a (minor) holiday, I still had a good audience of close to 30 people.

While I did not give that presentation again in Delhi, I did meet two ontologists two days later in the Delhi area (Noida), Dr. Sanju Tiwari, who had been involved in the Knowledge Graph Conference, and Harish Betrabet, an ontologist at Bechtel.

Knowledge managers

Taxonomy work often falls under knowledge management, especially in the area of consulting.
I had noticed that one of my prominent LinkedIn contacts in India (with over 140 shared connections) was a leading knowledge management professional, Ved Prakash. Ved met with me and Soumyakanta for lunch my very first day in India. Ved and I have both been involved in Stan Garfield’s SIKM group of knowledge managers, and Ved invited me to now to join the KMGN (Knowledge Management Global Network) group on LinkedIn, which he leads. Knowledge management in India is more mature than the smaller field of taxonomies.

Academic librarians

I interact with librarians through my membership in the Special Libraries Association (SLA), which has an active Taxonomy Community. At last year's annual SLA conference at the University of Rhode Island, several academic librarians from India, who have been very involved in SLA, participated in the conference and also celebrated the 25^th anniversary of the SLA Asia chapter with an event which I attended. The director of the Central Library of the Indian Institute of Technology, Delhi, Nabi Hasan, invited to give a presentation, and then organized a full-day “International Workshop on Open Accessing Publishing” at IIT Delhi around my schedule. To tie taxonomies into the theme, I gave a new presentation “Semantic Standards and Methods for Information Linking.” The audience was not familiar with Semantic Web technologies, so I was pleased to present something new to them, which I hope they will take advantage of.

Former SLA president Seema Rampersad (working at the British Library in London) introduced me, at my request, to another library science professor at the University of Rajesthan in Jaipur, with whom I met on short notice the evening I was visiting that city as a tourist, and we discussed the state of library/information science study.

Technical writers and content managers

With the growth of technology industries and applications of technology in other manufacturing sectors in India, there are now many technical writers along with content/document managers. The Society for Technical Communications (STC) (of which I had previously been a member) has an active chapter in India, so I contacted STC India about organizing a speaking event for me, and I was very pleased that the STC volunteers organized events in both Bengaluru and the greater Delhi area (Noida) to fit my schedule.

The events also each included additional different speakers. I gave the presentation “Indexes, Search, and Taxonomies: Path to Findability,” which I had presented as an STC webinar (not in a suitable time zone for India) in 2023. Taxonomies and indexing are new concepts to many technical writers, whether in the U.S. or India. (My STC contact, Manisha Sardana, will be happy to arrange an event for other visitors to Delhi who want to give an educational presentation.)

Finally, I even met a freelance indexer, a member of the American Society for Indexing, another organization I have belonged to, who attended the STC event in Noida at my invitation.

Summary

I gave more presentations than I initially intended on this trip, but that is partly due to the fact that taxonomies cross over into multiple fields. I then got to meet more people, build and strengthen relationships, and reflect on the field and applications of taxonomies more. The professional activities took three days, while sightseeing took 10 days of my two-week trip. I hope to add on a professional speaking event on future international tourist trips, although I cannot imagine any other country besides India that would offer so many opportunities.

 

Ontologies vs. Knowledge Graphs

At the Connected Data London (CDL) conference I attended last week, ontologies were humorously referred to as the “O” word. The thought was that, until recently, experts preferred not to mention “ontology,” lest they alienate their audience, customers, or stakeholders. The word comes across as too technical. It is a term from philosophy, after all, and it does not help that it sounds very similar to “oncology” (as “taxonomy” has been confused with “taxidermy”). The term “knowledge graph” on the other hand, is more user friendly, and even if it is not perfectly understood, its general meaning can be guessed. Thus, people would refer to knowledge graphs regardless of whether they meant a knowledge graph or an ontology.

At the conference, however, it was discussed that there is a growing acceptance of the word “ontology,” not just among experts but also among varied stakeholders who need to implement them. This was noted by several conference speakers, especially in the wrap-up panel session for the Data Modeling track, which was titled “The ‘O’ Word: How Ontologies Drive Interoperable Data and Business Innovation.” The panel moderator Katariina Kari explained that this recent shift has happened because of LLMs, explaining: “We need a reliable natural language repository. LLMs works on a network of mimicking language, LLMs are primed for language.” So, now use of the word ontology can even help a startup get funding from venture capitalists, she observed.

However, there remains some confusion over what an ontology is. At one end there is the difference between ontologies and taxonomies, and at the other end the difference between ontologies and knowledge graphs. I clarified the distinction between taxonomies and ontologies in a prior blog post, “Taxonomies vs. Ontologies” (January 2023). While knowledge graphs are a relatively new concept, and ontologies have existed for much longer, it is the varied understanding of ontologies that has given rise to confusion.

An ontology is defined as a model of a domain of knowledge, which comprises classes (sets of things), attributes (types of characteristics of things) and relationships between classes. According to this definition, an ontology is a somewhat generic model of a domain, and it does not include all of the individual members or instances of each class (such as the names of individual companies in the class called Company) nor the specific attributes of each attribute type (such as the address of each specific company for the attribute type called Address).

However, the W3C recommendation for ontologies, OWL (Web Ontology Language) includes the designation “individuals,” and ontology software tools, such as Protégé, support the inclusion of individuals and their specific attributes. Thus, it is easy to think that an ontology, by definition, includes all specific individuals. But just because OWL covers the recommendation for how to include instances of a class, and software supports the inclusion of instances of classes does not necessarily mean that the instances or individuals are actually a component of an ontology. The ontology experts on this CDL conference panel confirmed that an ontology is the upper-level semantic model.

Then, what do we call an ontology plus all of the individual members (instances) of classes and their specific attributes? That is essentially what a knowledge graph is. This is especially true when individuals are specific to an organization or enterprise, such as names of individual customers, products, employees, etc., and we call that an “enterprise knowledge graph.”

The first applications of ontologies in information/data science were in biomedicine, in which individuals included such things as names organisms (including bacteria and viruses) and chemicals, etc. Thus, the notion of an individual in science is not quite the same as in business, which has also been a source of confusion over what an individual is and the inclusion of individuals in an ontology. In enterprise knowledge graphs, the instances can be very numerous and specific, including individual “events,” such as interactions or transactions.

In conclusion, an ontology is typically a defining feature and component of a knowledge graph, but it is not all of what goes into a knowledge graph. A knowledge graph also includes individuals, which may be named entity instances or they may be specific taxonomy concepts (abstract things that are not unique named entities, such as the concepts “Data ethics” or “Performance measurement”), and a knowledge graph also includes specific attributes of individuals. It may be said that a knowledge graph is the instantiation of an ontology, and an ontology is the knowledge model. Katariina further explained: “knowledge graphs that actually follow an ontology will have an LLM perform better than just a KG that is unharmonized, not yet adhering to a clear ontology.”

The Semantic Data Conference

I was honored to be accepted to speak at the first “Semantic Data” conference in New York, a one-day event held on October 23, following the inaugural event held in London on June 27. Semantic Data, organized by Henry Stewart (HS) Events, is co-located with its better-known DAM (Digital Asset Management) conference, which has been running for over 20 years in New York, London, and Los Angeles.

The full name of the conference was “Semantic Data: Taxonomy, Ontology, and Knowledge Graphs,” so the conference was less focused on data then on what you can do with data and content when combined with the semantics of taxonomies and ontologies. There was no presentation dedicated to knowledge graphs this time, with only sessions in the single-day one-track event. Less of a focus on knowledge graphs was fine, since the Knowledge Graph Conference, held in New York in May covers that topic very thoroughly over multiple days. The emphasis on “semantics,” though, is welcome, since there is no conference dedicated to that subject in the United States. (There is the SEMANTiCS conference in Europe, but it is semi-academic.)

 

Presentations at Semantic Data, New York

The topics of the sessions for the “Semantic Data” included: securing taxonomy and ontology strategy buy-in, why and how to connect taxonomies and ontologies, use of MS Copilot in taxonomy development, a use case in leveraging an LLM-based for content integration and a consumer-based semantic layer, and how to apply semantic models (taxonomies and ontologies) that reduce biases, especially for machine learning models. The opening keynote by Lulit Tesfaye was on realizing the semantic layer keynote, and the closing keynote by Gary Carlison and Bramm Wessel of the lead sponsor, Factor, was on building an organization semantic mindset. Additional sponsored talks were on how ontologies accelerate innovation in the life sciences, as done by the sponsor SciBite, and how semantics enhances modern data platforms, such as the sponsor Datavid.

I presented “Taxonomies to Ontologies: How When and Why to Connect or Extend.” I summarized the benefits of taxonomies and ontologies, including what you could or could not do with each alone, but what you could do with both combined. The fact that both taxonomies and ontologies are now based on compatible Semantic Web standards, which are supported by many tools, makes it easy to combine or extend them. Whether you are “combining” a taxonomy with an ontology or “extending” a taxonomy into an ontology depends merely on your starting point and definition of ontology. Now that I am again vendor neutral, I included screenshots from four different commercial tools for combined taxonomy/ontology management.

About the Semantic Data Conference 2024

Semantic Data New York was similar to Semantic Data Europe (London) in its format and organization. Both provided a combination of session types: instructional talks, industry use cases, round table participant discussions, and thought leadership panels. Both events were chaired by Madi Weland Solomon and featured the same keynote presentation by Lulit Tesfaye on the subject of the semantic layer. The rest of the speakers were different at both events, and each event had different sponsors, based on geographic location. While there were only three sponsors of Semantic Data in New York and only two in London, they shared the same exhibit hall with the main DAM (digital asset management) and thus reached a wider audience.

Attendees of both the London and New York events had a similar number of registrants, about 50. Although the larger co-located DAM conference had separate registration, some registrants of the DAM conference were also seen in Semantic Data sessions. Registrants of Semantic Data represented diverse industries, including financial services, healthcare, software/technology, media, entertainment, publishing, travel and tourism, education, government, and consulting. Roles were also diverse, including company leadership, project and program managers, IT, and content/DAM/taxonomy/information architecture practitioner roles.

I find that the distinction between the roles and activities of taxonomists, ontologists, information architects, digital asset managers, etc. overlaps, so a conference dedicated to semantics brings them together for shared knowledge sharing. This way, their projects can also be broadened and shared within their organizations. I hope the Semantic Data conference can grow in the future to fill this need, and I look forward to next year.

Generative AI at Taxonomy Boot Camp Conference

Generative AI and large language models (LLMs), the technology behind ChatGPT, have been topics of presentations, keynotes, and attendees’ conversations at all the varied conferences I had the fortune to attend this year, including the Taxonomy Boot Camp conference held November 6-7, in Washington, DC. Taxonomy Boot Camp is the only conference dedicated to taxonomies.

Opening and Keynotes

 

Right from the beginning in the opening welcome, the conference chair Stephanie Lemieux mentioned uses of ChatGPT for taxonomy creation, such as asking prompts: What is a category for a following list of terms?, What label for a concept might be better for scientists, or better for parents?, and What are alternative labels for a specific content? It has become clear that generative AI is a tool to assist taxonomists with specific tasks of a project but is not appropriate for automating the entire creation of a taxonomy. Thus, the Taxonomy Boot Camp theme this year, “Humans in the Loop,” was quite apt for the new era of generative AI, even if not specific to it.

 

The Taxonomy Boot Camp opening keynote, “Ontologies in the New Age of AI” by Dean Allemang, was on this subject. Dean is more of an ontologist than a taxonomist, hence the title, but he discussed both taxonomies and ontologies. Allemang made the statement that Generative AI “understands” why we need a taxonomy (even if managers do not). He explained that Schema.org has put RDF on many websites, which ChatGPT “reads.” Allemang has found that ChatGPT also performs perfectly on SPARQL queries, the query language for data, including taxonomies, that is in RDF. Allemang gave ChatGPT query examples, such as “Return all the claims we have by claim number, open date, and close date,” and “What is the total loss of each policy where loss is the sum of loss payment, loss reserve, expense, payment, and expense reserve amount?” Allemang advised taxonomists to identify uses for taxonomies that have not been fully delivered on and use generative AI to deliver it, and if people argue that generative AI does not understand their language, taxonomists should build in a link to the taxonomy that makes generative AI understand it.

 

On the second day, Taxonomy Boot Camp registrants  attend the same shared keynote presentations with all of the KMWorld co-located conferences, and this year these mostly dealt with generative AI, including the opening keynote by Dion Hinchcliffe “Tech-Driven Enterprise Thrills & Chills: The Future of Work.” 

Regular Sessions

In addition to being mentioned in various talks, generative AI was also the subject of a session, “ChatGPT, Taxonomist: Opportunities & Challenges in AI-Assisted Taxonomy Development,”  which comprised two separate presentations.

In this session, Xia Lin presented in “Chat GPT and Generative AI for Taxonomy Development” in which he discussed the steps involved in using ChatGPT in two case studies. In one, a taxonomy for data analytics projects of a small business was developed by providing ChatGPT with the scope of the first level of the taxonomy and then asking ChatGPT to expand individual categories by adding subcategories and then to add definitions of terms and categories. The results were reviewed and revised by experts. But Lin did not stop there. He showed the results of asking ChatGPT to provide stakeholder interview questions around a category, and (for those more technically inclined) how to create a ChatGPT plug-in for various defined functions of taxonomy creation, using ChatGPT’s APIs. 

Also in “ChatGPT and Generative AI for Taxonomy Development” Marjorie Hlava and Heather Kotula jointly presented on issues of the use of ChatGPT to create taxonomies and in general. They explained the risks of bias, plagiarism, ethics, data quality, matching the generated taxonomy to the content, and the amplification of errors upon repeating a prompt. In plagiarism, for example, if you ask ChatGPT to return a complete taxonomy on a subject domain in may return a copyrighted taxonomy that cannot be reused without a license.

Generative AI also impacts the topics of other presentations. For example, in the presentation “In Taxonomy We Trust: Building Buy-In for Taxonomy Projects,” Bonnie Griffin mentioned the importance of “continually re-introducing the value of taxonomy, as generative AI captures attention.” It was also the subject of a debate question in somewhat humorous closing sessions “Taxonomy Showdown—Point/Counterpoint With Taxonomy Experts.”

 

More on Taxonomies and AI

Of course, there is more to AI than just generative AI. Other sessions dealt with machine learning for auto-categorization. These included presentations by each Bob Kasenchak and Rachael Maddison in the session “Machine Learning Is Coming forYour Taxonomy,”  (link to Bob’s slides)  and Wytze Vlietstra’s presentation of  “Vision for Modular Taxonomy Product at Elsevier,” in which the program included “shared infrastructure supported by AI-based decision support tools.” In fact, AI has been a theme of Taxonomy Boot Camp in the past, in 2018. It is generative AI based on large language models that is new. 

For some more details on how this technology may be used for taxonomy development, see my prior blog post this spring “Taxonomies and ChatGPT.”  To get another perspective on this conference, check out the recent blog post by Taxonomy Boot Camp speaker Mary Katherine Barnes “Integrating AI: Insights from KMWorld 2023.”

SEMANTiCS Conference 2023: Taxonomies, Knowledge Graphs, and LLMs

The most recent conference I participated in was SEMANTiCS, September 20-22, in Leipzig Germany. This was the 19th year of this European conference focused on the application of semantic technologies and systems. This was also my fourth year presenting a workshop/tutorial on taxonomies and ontologies at the conference. The widespread value of taxonomies across different areas of specialization is indicated by the fact that taxonomy workshops are repeatedly a part of conferences on various subjects, including semantics, knowledge management, library and information science, information architecture, content strategy, and  digital asset management.

Semantics and taxonomies

Semantics means “meaning,” so semantic systems utilize standards to support the encoding of meaning of things/resources and their relations, making the semantics machine-readable. Various standards, guidelines, and data models for semantic systems were developed for what is called the Semantic Web. The Semantic Web goes beyond the simple hyperlinks of the World Wide Web to label shared metadata, specify the kinds of relations. This supports linked data, and the linking of taxonomies to other taxonomies and ontologies and their tagged content or data, which are stored on different servers. 

Just as World Wide Web protocols have been adapted within enterprises (“behind the firewall”), so have Semantic Web standards. You don’t have to share your data publicly to reap the benefits of the Semantic Web: open standards to enable the migration of taxonomies and related data between systems, sharing of data with partners, extracting and transforming data from within silos across the enterprise into a standard format, and the ability to link to data on the Web to bring in new content even if not sharing content out on the Web.

Taxonomies, as controlled vocabularies, have always been about concepts, each with unique understood meaning, not just words or strings of text. So, using taxonomies is using semantics. The Semantic Web standard SKOS (Simple Knowledge Organization System) specifies a data model to make taxonomies and other knowledge organization systems (thesauri, classification systems, etc.) machine-readable and interchangeable on the Web. Semantic Web standards also cover ontologies with RDF-Schema and OWL. By following Semantic Web Standards, taxonomies can easily be linked to and extended with ontologies, and then by linking to data stored in a graph database, knowledge graphs can be built.

The SEMANTiCS conference

The SEMANTiCS conference is somewhat unique by being semi-academic and semi-industry. It has separate academic track and industry track chairs and additional tutorials and workshops. It’s good to bring academia and industry together in a field like this, where research topics can be applied and partnerships can be developed. The location of the conference varies, and it partners with a local higher education institution for logistical support, with graduate students volunteering to help in exchange to getting access to sessions. 

This was the second year that SEMANTiCS combined its conferences with the Language Technology Industry Association, which organized a Language Intelligence track, dealing with technologies for the management of terminology, multilingual content, and machine translation. The conference also includes a one-day track focused on DBpedia, which is not the same first day as the tutorials and workshops. The entire conference lasts three full days, and has a social event one evening, and a dinner on the second evening.  

The conference has industry vendor sponsors, about eight of which were exhibiting, and a few more which did not exhibit. There are also slightly more organizations which are “partners,” including DBpedia, The Alan Turing Institute, and a number of institutes of higher education in Europe which have programs in semantic technologies. Additional organizers include Semantic Web Company, Institut für Angewandte Informatik and the Vjije Universities Amsterdam, representing the three countries where SEMANTiCS has been taking place: Austria, Germany, and Netherlands. 

SEMANTiCS 2023

The 2023 conference was held September 20-22 in Leipzig, Germany, under the leadership of a new chair Sahar Vahdati of Technical University Dresden. There were about 285 participants in person and about one-third as many online. The conference has been hybrid since 2021. There were often six simultaneous sessions. Themed tracks or sessions of multiple speakers included Knowledge Graphs, Reasoning & Recommendation, Natural Language Processing and Large Language Models, Legal & Data Governance, Ontologies Data Management, and Environmental-Social-Governance (ESG). While there was not a life sciences track like last year, there was a themed subject track on cultural heritage. LLMs and ESG were both new topics this year. Poster presentations also covered the range of topics. 

Knowledge graphs is a regular theme at this conference, but this time there was the addition of LLMs. The opening keynote was “Generations of Knowledge Graphs: The Crazy Ideas and the Business” presented by Xin Luna Dong of Meta. She spoke of three generations of knowledge graphs: entity-based knowledge graphs, text-rich knowledge graphs, and dual neural knowledge graphs, using an ontology and LLMs. The second day’s keynote was “Knowledge Graphs in the Age of Large Language Models,” presented by Aiden Hogan of the University of Chile. LLMs and AI topics were also presented in the Knowledge Graphs track, such as in Andreas Blumauer’s talk “Responsible AI and LLMs.” Finally, the moderated closing panel was “Large Language Models and Knowledge Graphs: Status Quo - Risks - Opportunities” with panelists, Andreas Blumauer and Jochen Hummel from software vendors and Kristina Podnar, a digital policy consultant, who were not completely in agreement.

In addition to my 3-hour tutorial, “Knowledge Engineering of Taxonomies and Ontologies,” only slightly updated from last year, I also contributed, along with Lutz Krüger, to Andreas Blumauer’s new 3-hour tutorial “They Key to Sustainable Enterprises: ESG, KNowledge Graphs, and Digitalization.” Adopting an ESG program and complying with upcoming ESG directives requires connecting a lot of information and data and aligning it with requirements and disclosure categories, and this is where a knowledge graph can be extremely helpful. Other tutorials and workshops dealt with data spaces, ontology reasoning, healthcare NLP, NLP for knowledge graph construction, and FAIR ontologies. 

Past and future

Semantic technologies were very new when the conference was first launched in 2005 by Semantic Web Company, even before launching its product PoolParty Semantic Suite. But it’s never been a vendor product-based conference. The main purpose was and still is to promote the understanding and advancement of semantic technologies. Competitor software vendors sponsor and exhibit, and Semantic Web Company has stepped back from a lead organizational role. The conference is not one where sponsors make business in selling their products or services, but rather for raising awareness, making and reinforcing partnerships, exchanging ideas, and general networking, including looking for work. It is more of a community conference than anything else, but it is an open welcoming community, with new people coming every year.

The next SEMANTiCS, celebrating its 20th year, will be September 16 - 18, 2024, in Amsterdam.