Hi everyone!
(Sorry for the wide distribution list, I hope this is not too drastic
spamming.)
We at Ontotext are highly interested in all kinds of LLM scenarios and
applications, especially LLM-KG synergy.
We have many clients and prospects that want to "talk to their KG", and are
working in this direction.
GraphDB 10.3 and 10.4 introduce progressively more elaborate LLM
integrations.
Edlira Vakaj and co-authors just released a major study "Large Language
Models and Knowledge Graphs- Opportunities and Challenges (2023-10)" on
arXiv.
We are looking for use cases and collaborations in this direction. Here are
some brief ideas:
- Semantic BSDD: natural language querying, where LLM is used to
generate GraphQL queries. I've recorded a video, but the demo is not
productized: copy & paste from ChatGPT to GraphiQL query editor
- Using LLM for NLP tasks related to regulations: we did early
experiments with LLM (eg "parse this regulation according to the RASE
methodology")
- Automated classification or normalization: AFAIK, Petr Hradil
and Markku Kiviniemi are looking for ways to match free-text descriptions
of materials to data dictionaries like BSDD
If you are interested in a collaboration or have a use case that we could
help to implement, please reply.
(Consider whether you want to reply to all, or a smaller list of people)
Cheers!