Tomorrow, 29th January at 12 noon CET, I will participate in an online panel discussion titled "Artificial Intelligence in Knowledge Organisation", organised by Linnaeus University (Sweden).
"This two-hour panel brings together leading experts to explore how AI transforms knowledge organization in libraries and related cultural heritage institutions as well as research data services."
More info and Zoom link:
Version 1.4 of the Annif automated subject indexing tool has been released! 🚀
• 3 new corpus formats (JSON, JSONL, CSV) supporting metadata + document IDs
• Include/exclude vocab concepts for better control
• annif index now supports short-text formats
• Faster hyperopt with parallel processing
• tfidf backend refactored (no gensim!)
• REST API improvements & Python 3.13 support
https://github.com/NatLibFi/Annif/releases/tag/v1.4.0
#Annif #NLP #opensource #subjectindexing #machinelearning #code4lib #libraries
In the first #LLMs4Subjects challenge at the SemEval-2025 workshop, our #Annif team did very well!
The challenge was to generate good quality subject indexing for bibliographic records in German & English using LLMs. We used LLMs for data preprocessing (translation & synthetic data) and Annif as the main suggestion engine. We ranked 1st and 2nd in quantitative and 4th in qualitative evaluations out of 14 teams!
More info & preprints: https://groups.google.com/g/annif-users/c/b8kVy6XSzB4/m/JE6xBzSuEgAJ
Last November we organized a survey for Annif users, and now the results have been published in the Doria repository of the National Library of Finland:
https://urn.fi/URN:ISBN:978-952-84-1301-1
The report includes an overview of:
- The vocabularies and datasets that are used with Annif
- The workflows that Annif is integrated with
- The problems Annif users are facing
Version 1.3 of the automated subject subject indexing tool #Annif has been released!
This release introduces support for the EstNLTK analyzer for better Estonian lemmatization 🇪🇪, optimizations to the MLLM backend, as well as maintenance and bug fixes, including better file permissions in multi-user environments.
https://github.com/NatLibFi/Annif/releases/tag/v1.3.0
#AI #machinelearning #opensource #code4lib #libraries #subjectindexing #SKOS #classification #Estonian #eesti
Are you using #Annif for automated subject indexing or classification? Have you tried it out? Did you look at it but never got around to using it?
If yes, please fill in this Annif user survey: https://forms.gle/P7jGoPMbEAJnD9zw9
We want to hear your thoughts about Annif and how to make it better in the future!
It should only take a few minutes. Deadline is November 30.
#Annif #AI #subjectindexing #libraries #automation #SKOS #code4lib #survey
Welcome to the Annif users survey! The survey aims to gather information mainly about how Annif is being used and with which vocabularies and datasets, Annif could be improved and which directions to take in the future, Annif community could be activated to enhance collaborations. The survey should take between 5 to 15 minutes to complete. The responses or results are not shared in a way which allows identifying individual responders. Feel free to share the survey link to relevant parties! The survey will remain open until 30th November 2024. In case of any problems or questions about the survey, please contact the Annif team at the National Library of Finland via [email protected]. Thank you for your participation and valuable contributions!
We will organize an #Annif tutorial session "Introduction to the Annif automated indexing tool" at the #SWIB24 online conference on 25th November 2024, 9-13 CET! It's free, but you need to sign up through the SWIB Discourse platform: https://forum.swib.org/t/workshop-introduction-to-annif-automated-indexing-tool-category/139
The workshop is based on the Annif tutorial materials, created by the National Library of Finland and ZBW: https://github.com/NatLibFi/Annif-tutorial
#AI #machinelearning #code4lib #opensource #libraries #SKOS #subjectindexing #classification
Facilitator @Osma , Mona Lehtinen, Juho Inkinen, @AnkasZBW , Ghulam Mustafa Majal, Lakshmi Rajendram Bashyam Abstract Many libraries and related organizations are exploring automated methods for metadata creation. This workshop offers an introduction to the multilingual automated indexing tool, Annif (annif.org), which can be integrated into a library’s metadata production system. Participants will gain hands-on experience with Annif by setting it up, training its algorithms with sample data, ...
The automated subject indexing tool #Annif version 1.2 has been released! This release adds API and CLI functionality for language detection (based on the #Simplemma library), automated download of NLTK data packages, full support for Python 3.12, a few bug fixes and upgraded dependencies.
#AI #machinelearning #opensource #code4lib #libraries #subjectindexing #SKOS #classification
Osma Suominen
Finto-palvelu
v_i_o_l_a