
Student turned Data Scientist turned back to student. PhD candidate @VUAmsterdam & #DiscoveryLab, working on ML on graphs for hypothesis generation.
Amsterdam, The Netherlands
Joined October 2017
- Tweets64
- Following213
- Followers100
- Likes254
Dimitris Alivas retweeted
Our work on embedding multimodal biomedical knowledge graphs is now published at the Journal of Biomedical Semantics @BioMedCentral!
Read the paper here: doi.org/10.1186/s13326-023-0…
New preprint! We introduce BioBLP, a method for learning embeddings on multimodal knowledge graphs.
Paper: arxiv.org/abs/2306.03606
Code: github.com/elsevier-AI-Lab/B…
w/ @DimitrisAlivas @pmitra01 @thompijn @michaelcochez @pgroth
1/4
Dimitris Alivas retweeted
The neural query answering crowd of @michaelcochez, @DimitrisAlivas, @_kire_kara_ , @BerrendorfMax, @danieldazac, @PMinervini, @Mniepert, @ren_hongyu, (and yours truly) contributed Chapter 17 about Approximate Answering of Graph Queries to this monumental book. Check it out!
The new edited book
Compendium of Neurosymbolic Artificial Intelligence
is now available - 30 chapters (700 pages), each conveying integrated content from several published papers of recent years.
iospress.com/catalog/books/c…
Dimitris Alivas retweeted
We are hiring! 🎓
Are you interested in working on the combination of Knowledge Graphs and Large Language Models with @FrankVanHarmele and me?
Apply here for a PhD position at @VUamsterdam:
workingat.vu.nl/ad/phd-posit…
#knowledgegraphs #languagemodels #machinelearning
Dimitris Alivas retweeted
Today it's ten years since Wikidata had launched, October 29, 2012.
A few memories. 1/
Dimitris Alivas retweeted
Jan-Christoph Kalo is sharing his work on Prompting as Probing: Using Language Models for Knowledge Base Construction.#iswc_conf #iswc2022
Dimitris Alivas retweeted
"Prompting as Probing: Using Language Models for
Knowledge Base Construction" based on @wikidata
(Alivanistos et al, 2022)
arxiv.org/pdf/2208.11057.pdf
@ThiviyanSingam @EmilevanKrieken
@JanCKalo @michaelcochez
Dimitris Alivas retweeted
Another win this summer! 🔥🔥🔥
A collaboration between the @krr_vu and @CLTLVU labs, where #NLProc meets #KnowledgeGraph
It was super fun and enriching to work with @DimitrisAlivas @michaelcochez @EmilevanKrieken @JanCKalo and @ThiviyanSingam, thank you for the experience!!
We are excited that our team won the @lm_kbc @iswc_conf 22 competition!
We do Knowledge Base Construction using @OpenAI GPT-3.
Our conclusion: Size gets you more than prompt engineering.
arxiv.org/abs/2208.11057
(1/n)
Dimitris Alivas retweeted
Wanna work at the most exciting boundary in modern AI (combine machine learning and symbolic reasoning), and use it to improve drug safety for kidney patients, in a leading AI team, jointly with medical researchers? Apply for our PhD vacancy before 1 Sep! werkenbij.vu.nl/ad/phd-posit…
Dimitris Alivas retweeted
#hhai2022 Welcome to HHAI2022, the first conference in Hybrid Human Artificial Intelligence, which is going to take place in Amsterdam 13-17.June 2022. Watch this space.
Dimitris Alivas retweeted
How to estimate gradients on stochastic computation graphs with low variance?
Check out our poster @NeurIPSConf on our new framework & PyTorch library "Storchastic"!
Thu 17:30 CET neurips.cc/virtual/2021/post…
Paper: arxiv.org/abs/2104.00428
Library: github.com/HEmile/storchasti…
Dimitris Alivas retweeted
#ACL2021NLP I compiled a *short* overview of ~30 #KnowledgeGraph papers presented at ACL'21 @aclmeeting - neural databases, retrieval, KG embeddings, entity linking, QA, a bunch of new datasets, and (of course) some memes ☺️
#ACL2021 #NLProc
mgalkin.medium.com/knowledge…
Dimitris Alivas retweeted
Fascinating! arxiv.org/abs/2102.12846
Dimitris Alivas retweeted
Are you interested in #ArtificialIntelligence ? Looking forward to working at the bleeding edge of the field? Not afraid of working with a mix of structured and unstructured data? Then apply as a #postdoc at our Discovery Lab! workingat.vu.nl/ad/postdocto…
Dimitris Alivas retweeted
For the Linked Data music enthusiasts (and everybody else too!): you can find all MIDI Linked Data stuff at midi-ld.github.io #dhbenelux #eswc2018 #linkedconferences























