I am interested in these questions and how one can mix hard requirements from text and soft LLM queries. Especially around regulatory and other real requirements. This can be different from information requirements which are (sometimes) negotiable.
Sent whilst away from my desk.
Regards,
Nick.
Nicholas Nisbet FRSA MA(Cantab) DipArch(UNL)
Fellow: Royal Society of Arts
Fellow: buildingSMART International & UKI Chapter
Director: AEC3 UK Ltd
Web: http://www.aec3.com<http://www.aec3.com/>
E-mail: nn@aec3.com<mailto:nn@aec3.com>
Direct: +44 (0) 1494 714 933
Mobile: +44 (0) 781 616 8554
Registered Address: 46 St Margaret's Grove, Great Kingshill, High Wycombe, Bucks, HP15 6HP, UK
Vice-Chair: buildingSMART UK Chapter
Convenor: buildingSMART Regulatory Room
********** Confidentiality Notice **********.
This e-mail and any file(s) transmitted with it, is intended for the exclusive use by the person(s) mentioned above as recipient(s). This e-mail may contain confidential information and/or information protected by intellectual property rights or other rights. If you are not the intended recipient of this e-mail, you are hereby notified that any dissemination, distribution, copying, or action taken in relation to the contents of and attachments to this e-mail is strictly prohibited and may be unlawful. If you have received this e-mail in error, please notify the sender and delete the original and any copies of this e-mail and any printouts immediately from your system and destroy all copies of it.
On 11 Oct 2023, at 19:05, Vladimir Alexiev <vladimir.alexiev@ontotext.com> wrote:
EXTERNE-EMAIL Bitte klicken Sie nicht auf Links oder öffnen Sie keine Anhänge! Es sei denn, Sie kennen den Absender und wissen, dass der Inhalt sicher ist.
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!