Internship | Exploring the utility of large language models for achieving semantic interoperability

The ability of IT systems to exchange data with unambiguous, shared meaning is called semantic interoperability. TNO fosters semantic interoperability in Dutch economic sectors (e.g. flexible staffing, logistics or manufacturing industry), but even in these relatively homogenous business communities it takes a lot of effort by everyone involved to use a single ‘language’ when exchanging data. It requires community building around a clear vision of interoperability, creating open semantic standards with that community, setting up and running open governance processes for these standards, regular communication about new developments, and constant implementation support services. While there have been European developments in the field of semantic standardization, some with reasonable success, they have so far not been enough. As the BRIDGE Data Management working group puts in in their 2019 report: "Efforts to achieve interoperability have been delivered for decades by highly motivated and skilled professionals. There can be little doubt that the communities involved have been "doing things rights" for many years. Yet, the result do not address the challenges adequately."

Problem statement:
Meanwhile the world of artificial intelligence has given rise to groundbreaking technologies such as large language models (LLMs) and other ML/NLP techniques. Could these provide an opportunity to disrupt the way the issue of semantics has been approached in the last decades and boost semantic interoperability in data spaces? A so-called data space is a framework that supports data sharing within a data ecosystem.

The problem can therefore be specified as such: how can we harness the power of LLMs and related technologies to foster semantic interoperability in the context of European data spaces? The specific context in which this problem will be explored is that of the Enershare project, which aims to create a data space for the energy domain.

Assignment:
To achieve semantic interoperability TNO has built a software platform called ‘Vocabulary Hub’ that serves to encourage vocabulary (re)use by data providers. It is a web application that contains a repository of standardized vocabularies (e.g., RDFS/OWL ontologies, XML Schema, JSON Schema) relevant to the energy domain. One of the way the Vocabulary Hub is expected to encourage vocabulary reuse is through features that allow data providers to annotate their own data set by mapping data fields to the terms in some existing vocabulary. Unfortunately creating mappings like these is no easy task, and it requires semantic modelling expertise that most of these users are lacking. What vocabulary to use? What do these concepts and properties mean? Which one is the most closely related to my data, and how exact is that match?

The assignment is to explore if LLMs or similar ML technologies can support this mapping task by creating a software prototype and demonstrating its functionalities and limitations to the TNO team.

The TNO Vocabulary Hub provides the technological context for your prototype. The Hybrid AI team at TNO is there as a source of knowledge about the new AI technologies.

We are looking for an enthusiastic, and curious student of software engineering (or related studies) looking for an internship. You should be willing to learn new technologies and are able to think through abstract concepts towards their practical implication. In addition, communication is key since the assignment consist of combining knowledge from different disciplines and teams in the organization.

The assignment is to explore if LLMs or similar ML technologies can support this mapping task by creating a software prototype and demonstrating its functionalities and limitations to the TNO team.

The TNO Vocabulary Hub provides the technological context for your prototype. The Hybrid AI team at TNO is there as a source of knowledge about the new AI technologies.

You want to work on the precursor of your career; a work placement gives you an opportunity to take a good look at your prospective future employer. TNO goes a step further. It’s not just looking that interests us; you and your knowledge are essential to our innovation. That’s why we attach a great deal of value to your personal and professional development. You will, of course, be properly supervised during your work placement and be given the scope for you to get the best out of yourself. Naturally, we provide suitable work placement compensation.

At TNO, we innovate for a healthier, safer and more sustainable life. And for a strong economy. Since 1932, we have been making knowledge and technology available for the common good. We find each other in wonder and ingenuity. We are driven to push boundaries. There is all the space and support for your talent and ambition. You work with people who will challenge you: who inspire you and want to learn from you. Our state-of-the-art facilities are there to realize your vision. What you do at TNO matters: impact makes the difference. Because with every innovation you contribute to tomorrow’s world. Read more about TNO as an employer.

At TNO we encourage an inclusive work environment, where you can be yourself. Whatever your story and whatever unique qualities you bring to the table. It is by combining our unique strengths and perspectives that we are able to develop innovations that make a real difference in society. Want to know more? Read what steps we are taking in the area of diversity and inclusion.

After the first CV selection, the application process will be conducted by the concerning department. TNO will provide a suitable internship agreement. If you have any questions about this vacancy, you can contact the contact person mentioned below.

Students must reside in the Netherlands before the start and also throughout the internship or graduation project at TNO.