I'd like to share a little tool that I created that I've been playing with. I think now is the time to share it because I believe it has a unique solution to the "how do you chunk up a document" for #LLM #embeddings, which is something @simon mentioned being an open challenge in his recent blog post.

I've been calling it Semeditor, short for Semantic Editor, available here: https://gist.github.com/player1537/1c23b91b274d2e885be80d5892bac5b7

It can be run with `--demo` to get the text from the screenshot.

Zero-shot Node Classification with Graph Contrastive Embedding Network

https://openreview.net/forum?id=8wGXnjRLSy

#embeddings #graphcen #embedding

Semantic Representations of Mathematical Expressions in a Continuous Vector Space

Neeraj Gangwar, Nickvash Kani

Action editor: Yonatan Bisk.

https://openreview.net/forum?id=EWPA9TZcUy

#embeddings #expressions #representing

Of course I know RDF2vec ;-)
However, Heiko Paulheim's RDF2vec website has grown nicely and has become a rather valuable resource for this #knowledgegraph embedding method, including implementations, models and services, variations and extensions, as well as more than 150 references in scientific papers!
RDF2vec website: http://www.rdf2vec.org/
original paper: https://madoc.bib.uni-mannheim.de/41307/1/Ristoski_RDF2Vec.pdf
Petar Ristoski's PhD thesis (with RDF2vec): https://ub-madoc.bib.uni-mannheim.de/43730/1/Ristoski_PhDThesis_final.pdf
#kge #deeplearning #embeddings

SMGRL: Scalable Multi-resolution Graph Representation Learning

https://openreview.net/forum?id=ZBiXWM0AV8

#embeddings #graphs #nodes

'Insights into Ordinal Embedding Algorithms: A Systematic Evaluation', by Leena Chennuru Vankadara, Michael Lohaus, Siavash Haghiri, Faiz Ul Wahab, Ulrike von Luxburg.

http://jmlr.org/papers/v24/21-1170.html

#embeddings #embedding #ordinal

🧠 Realizzare un #chatbot o una ricerca evoluta per un sito web: quanto sarebbe stato complesso un paio d'anni fa (sono ottimista)? Tanto. Infatti pochi servizi erano davvero efficienti.
🦾 Nelle immagini si vede un'esempio di come l'ho creato con #Flowise.
👉 Un componente di scraping estrae tutti i contenuti dal mio sito web.
👉 Attraverso gli #embeddings di OpenAI vengono vettorializzati.
👉 I dati vengono salvati su un database vettoriale (#Pinecone).

#AI #IntelligenzaArtificiale #LLaMA2 #Claude

Multi-view Data Visualisation via Manifold Learning

https://openreview.net/forum?id=jMiwptYV5n

#embedding #embeddings #visualisation

💡 L'unione tra #LangChain e i #LLM ormai è abbastanza nota. L'obiettivo è produrre contesto per il modello per ottenere risposte, dati, informazioni relative ad un dominio definito.
🧠 #Embedchain è un framework in #Python che permette di creare un #chatbot basato su qualunque risorsa online.
🦾 Le risorse di riferimento vengono vettorializzate (#embeddings) e salvate in un database vettoriale.

#AI #IntelligenzaArtificiale

https://github.com/embedchain/embedchain

Over the last few weeks I was learning how to do better embeddings for NLP tasks, esp semantic search. But i couldn't figure out what to do with them afterwords, I deleted them all. Today, I watched a tutorial on embeddings and realized I could have visualized them! 🤦‍♀️ I had embeddings for different topics and languages, which would have been a great experiment to see how different models do embeddings differently. #embeddings #semanticsearch
#whydoidothistomyself

A jargon-free explanation of how AI large language models work – Ars Technica https://arstechnica-com.cdn.ampproject.org/c/s/arstechnica.com/science/2023/07/a-jargon-free-explanation-of-how-ai-large-language-models-work/amp/ (I like this one) #AI #technology #LLMs #transformerArchitecture #embeddings

As a 2nd topic of this last #ise2023 lecture, we were discussing #KnowledgeGraph Completion. Most simple approach for unsupervised #linkprediction based on (here translation-based) knowledge graph embeddings was explained on the example of Isaac Asimov.
Slides: https://drive.google.com/file/d/1atNvMYNkeKDwXP3olHXzloa09S5pzjXb/view?usp=drive_link
@fizise @enorouzi #scifi #knowledgegraphs #ai #deeplearning #embeddings

In today's #ise2023 lecture, we discussed neural networks, from the very simply McCulloch-Pitts Neuron up to Convolutional Neural Networks and Generative Adversarial Networks. A lot of content for only 90 minutes of lecture ;-)
Slides: https://drive.google.com/file/d/1KsAGBViEzu7UDkz-F2QJJJ23ce-AQ9pl/view?usp=drive_link
#machinelearning #deeplearning #representationlearning #knowledgegraphs #graphembeddings #embeddings #lecture @fizise @enorouzi #aiart #stablediffusionart

I've written a blog post which describes a solution in #csharp to use the #Chat and the #Embeddings functionality from #ChatGPT, combined with the #vector search capabilities from #Redis to ask questions about the contents of a #PDF document using natural language.

https://mstack.nl/blog/20230623-chatgpt-question-pdf-document/

Thanks @vicki for writing this article and @amcasari for pointing it my way. I finally got around to reading it, and it is an excellent and accessible introduction to #embeddings for #AI #ML #LLMs etc.

'Small Transformers Compute Universal Metric Embeddings', by Anastasis Kratsios, Valentin Debarnot, Ivan Dokmanić.

http://jmlr.org/papers/v24/22-1246.html

#embeddings #embedding #dimensionality

None of the commonly used #knowledgegraph #embeddings capture any semantics- leading us the the fundamental question What is Semantics? asks Frank van Harmelen in his keynote at #isws2023

A Bluffer’s Guide to #knowledgegraph #embeddings - Frank van Harmelen is the first keynoter at the International #semanticweb Research #summerschool #ISWS2023 with the title The K in neuro-symbolic stands for knowledge

'Asymptotics of Network Embeddings Learned via Subsampling', by Andrew Davison, Morgane Austern.

http://jmlr.org/papers/v24/21-0841.html

#embeddings #embedding #node2vec

Bram Steenwinckel from IDLab is presenting pyRDF2Vec at @eswc_conf !

#reasoning #Python #RDF #KnowledgeGraph #embeddings #MachineLearning #ESWC2023 #SemanticWeb #RDF2Vec