This week our colleague Ann Tan will present our work "The DDB Collection and the Challenges of Legacy Metadata" at #SWIB23
https://drive.google.com/file/d/1VkU1BLJPDlIZzevDCE09G025ebH8pvpe/view?usp=sharing
@fizise @epoz @tabea @sashabruns #ddb #digitallibraries #knowledgegraphs #semanticweb #reconciliation #gnd #frbr #ontologies

Happy to announce PyGraft, a configurable #Python tool to generate both synthetic #schemas and #knowledgeGraphs easily, supporting several RDFS and OWL constructs.

📄 https://arxiv.org/abs/2309.03685
💻 https://github.com/nicolas-hbt/pygraft (also available on PyPI)

We're hiring a Postdoc to work across NLP, Digital Humanities, and Semantic Web. https://www.rug.nl/about-ug/work-with-us/job-opportunities/?details=00347-02S000AC8P

Bring your creativity and skills to study the evolution of online fictional narratives https://golemlab.eu

@gronlp
#AcademicChatter
#DH #LinkedData #KnowledgeGraphs #nlproc @digitalhumanities @TedUnderwood @scott_bot @christof @fotis_jannidis @zoeleblanc @quinnanya @folgertk @melvinwevers @albertoacerbi @EvelynGius @DHd @dh_potsdam

11/end

[3] Previously: “Model Editing: Performing Digital Brain Surgery”. https://www.linkedin.com/posts/benjaminhan_llms-causal-papers-activity-7101756262576525313-bIge

[4] Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. 2023. Unifying Large Language Models and Knowledge Graphs: A Roadmap. http://arxiv.org/abs/2306.08302

#KnowledgeGraphs #GenerativeAI #LLMs #NLP #NLProc #Paper

8/ There are surely other benefits of using KGs to collect and organize knowledge. They do not require costly retraining to update, therefore can be updated more frequently to remove obsolete or incorrect facts. They allow more trackable reasoning and can offer better explanations. They make fact editing more straightforward and accountable (think of GDPR) compared to model editing [3].

#KnowledgeGraphs #GenerativeAI #LLMs #NLP #NLProc #Paper

7/ Their result shows that even #GPT4 achieves only 23.7% hit@1 on average, even when it scores up to 50% precision@1 using the earlier proposed LAMA benchmark (screenshot). Interestingly, smaller models like BERT can outperform GPT4 on bidirectional, compositional, and ambiguity benchmarks, indicating bigger is not necessarily better.

#KnowledgeGraphs #GenerativeAI #LLMs #NLP #NLProc #Paper

6/ In each benchmark, instead of asking LLMs to retrieve masked words from a cloze statement, it also asks the LLMs to retrieve all of the implied facts and compute scores accordingly (screenshot).

#KnowledgeGraphs #GenerativeAI #LLMs #NLP #NLProc #Paper

5/ Instead, they focus on more intricate topological and semantic attributes of facts, and propose 9 benchmarks testing modern LLMs’ capability in retrieving facts with the following attributes: symmetry, asymmetry, hierarchy, bidirectionality, compositionality, paths, entity-centricity, bias and ambiguity (screenshots).

#KnowledgeGraphs #GenerativeAI #LLMs #NLP #NLProc #Paper

3/ The result shows that even without specialized training, language models such as BERT-large can already retrieve decent amount of facts from their weights (screenshot).

#KnowledgeGraphs #GenerativeAI #LLMs #NLP #NLProc #Paper

2/ An early paper in 2019 [1] posited that compared to #KnowledgeGraphs, it is easier for language models to adapt to new data without human supervision, and they allow users to query about an open class of relations without much restriction. To measure the knowledge encoding capability, the authors construct the LAMA (Language Model Analysis) probe where facts are turned into cloze statements and language models are asked to predict the masked words (screenshot).

#NLP #NLProc #Paper

Dog Lenat, founder of #Cyc, passed away earlier this week. From Professor Ken Forbus:

"People in AI often don't give the Cyc project the respect it deserves. Whether or not you agree with an approach, understanding what has happened in different lines of work is important. The Cyc project was the first demonstration that symbolic representations and reasoning could scale to capture significant portions of commonsense…”

https://www.linkedin.com/posts/forbus_ai-knowledgegraphs-krr-activity-7103445990954700800-qcd-

#ai #knowledgegraphs #Reasoning #NLP #NLProc

The "Wikidata Research Articles Dataset" comprises peer-reviewed full research papers about Wikidata from its first decade of existence (2012-2022).
https://refubium.fu-berlin.de/handle/fub188/40510
@hcc_research
#Wikidata #research #dataset #knowledgegraphs #bibliography
via @wikiresearch (but posted on #twitter)

Next up at #JGI2023:

Cathy Wu from U. of Delaware

Integrative Text Mining and Graph Learning for Biological Discovery

#JGI #Bioinformatics #KnowledgeGraphs #ai #ml
@LBNLBioSci

Do you struggle with #SPARQL queries? Just ask #chatgpt to write you a query!
Wait....how about we train #llms to use different tools on #KnowledgeGraphs and store all of our knowledge in Knowledge Graphs?
What a brilliant future perspective with a lot of benefits by @vrandecic

https://sigmoid.social/@lysander07/110904664250735474

#wikidata #rdf #largelanguagemodels

Summer, sun and holidays...😎🌅 What better time to read and broaden your horizon? Check out our Blog to learn more about research in the context of #DigitalScience: https://www.uibk.ac.at/disc/blog/

Recent entries deal with ventilation of buildings and medieval mining.

#EnergyEfficiency #KnowledgeGraphs

@bsletten The #ise2023 summer lecture was not recorded. The intention was to bring students back to university lecture halls. There is a 80% overlap with the #ise2021 lecture which is already on #youtube. However, if you are interested in our latest lecture on #knowledgegraphs, don't miss the (free) #KG2023 online course "Knowledge Graphs - Foundations and Applications" on #OpenHPI which starts in Oct 2023.
https://open.hpi.de/courses/knowledgegraphs2023
@fizise @tabea @sashabruns @Hasso_Plattner_Institute

K-CAP 2023 submnission deadline extended: Abstract submission has been extended until August 27th, 2023, and paper submission is extended until September 1st, 2023, AoE.
12th International Conference on Knowledge Capture 2023
Website: https://www.k-cap.org/2023/cfp.html
#kcap2023 #conferences #deadline #cfp #knowledgerepresentation #knowledgecapture #ontologies #knowledgegraphs #deeplearning #ai

We are also looking for a #PostDoc / Senior Researcher for the interdisciplinary Leibniz Science Campus project "Digital Transformation of Research" on the effects of #AI on Research in different disciplines. This is a full position 100%, German TVöD-13 paygrade according to experience, limited to 4 years with the option of extension/tenure.
More information: https://www.fiz-karlsruhe.de/en/stellenanzeigen/postdocsenior-researcher-wmx-wissenschaftscampus-ditrare
Please distribute!
#knowledgegraphs #machinelearning #deeplearning #llm #semanticweb #linkeddata @fizise #jobad

We are looking for a #PhD / Junior Researcher OR #PostDoc / Senior Researcher for the Platform #MaterialDigital project for research on #ontologies, #knowledgegraphs, and #machinelearning for the #MaterialsScience Engineering domain. Full 100% position, German TVöD-13 paygrade according to experience, limited to 2 years first, with the option of extension/tenure.
For further information: https://www.fiz-karlsruhe.de/en/stellenanzeigen/phdjunior-researcher-oder-postdocsenior-researcher-wmx-plattform-materialdigital
MaterialDigital Website: https://www.materialdigital.de/
#jobad #academia #distribute

Our paper “Language Models as Controlled Natural Language Semantic Parsers for Knowledge Graph Question Answering” got accepted at #ecai2023. It shows that LLMs can learn controlled natural language with fine-tuning on limited training data. Details on our findings are here: https://amazon.science/publications/language-models-as-controlled-natural-language-semantic-parsers-for-knowledge-graph-question-answering
@amazon @SaharVahdati Preetam Gattogi, Dhananjay Bhandiwad Sébastien Ferré #LLM #KnowledgeGraphs