Відео

Thanks for the forecast! A bit off-topic, but I wanted to ask: My OKX wallet holds some USDT, and I have the seed phrase. (air carpet target dish off jeans toilet sweet piano spoil fruit essay). Could you explain how to move them to Binance?

thanks for presenting

good one!

What in the world are you saying!

I don't get the speech .She just talk about the simple structrue they use to build Kg.But the problem is how the base rules are defined and how to assess what attribute a forniture have.

Excellent presentation Denny!

Still didn't get clear definition of taxonomy vs ontology

Such a great presentation! I learned a lot, thank you!

Great podcast. A bit of feedback for the guy speaking at the beginning and at the 1 to 3 minutes marks....your audio is crackly and not really audible. Maybe look unto a better mic next time. Above all...Great topic!

Great talk. Thanks for your concise overview of the challenges implementing the concepts.

🎯 Key Takeaways for quick navigation: 00:00 *🎤 Introduction to Keynote* - Introduction to the keynote session by Denny Vrandečić from Wikimedia Foundation. 01:23 *🌐 Challenges and Changes in Knowledge Graphs and LLMs* - Knowledge graphs and LLMs are rapidly evolving, challenging existing paradigms. - Adoption of LLMs like GPT-3 has been unprecedented, impacting various sectors globally. - Researchers and practitioners are adapting to the implications of LLMs on knowledge graphs. 04:03 *⚠️ Narrow Focus and Disclaimers* - The talk specifically addresses the interaction between knowledge graphs and LLMs. - Disclaimers: The presentation does not include AI-generated content and avoids broader ethical and legal implications. 05:13 *🧠 Understanding Knowledge Graphs and Large Language Models* - Knowledge graphs represent relationships between entities, stored in graph databases like Wikidata. - Large language models (LLMs), exemplified by GPT-3, are neural networks trained on vast textual data. - LLMs, despite their capabilities, face challenges in computational efficiency compared to knowledge graphs. 10:23 *💡 Costs and Technical Challenges of LLMs* - LLMs incur high computational costs for both inference and training, posing financial and technical challenges. - Even with optimization efforts, LLMs remain computationally intensive compared to traditional knowledge graph lookup methods. - Industry leaders acknowledge the substantial computational overhead of LLMs. 11:33 *🔄 Evolving Landscape of LLMs* - The pace of change in the LLM landscape is rapid, with indications that the era of large language models might be waning. - Innovations like Meta's LLaMA model highlight the community's adaptability and creativity beyond GPT-3. - Technical limitations, including diminishing returns and cost concerns, influence the direction of LLM development. 12:53 *🌐 Challenges in Information Accuracy and Consistency* - Information accuracy and consistency pose challenges across platforms, exacerbated by reliance on sources like Wikipedia. - Discrepancies in information retrieval from platforms like Google, Bing, and LLMs reflect broader issues in data accuracy and verification. - Language-specific variations in information retrieval underscore the complexities of maintaining accurate knowledge bases. 17:01 *🤔 Limitations and Inefficiencies of LLMs* - LLMs exhibit limitations in handling specific queries, particularly those requiring mathematical operations or nuanced understanding. - The efficiency and reliability of knowledge retrieval through LLMs are questioned compared to structured knowledge bases like Wikidata. - Alternative approaches, such as augmented language models, offer potential solutions to mitigate LLM limitations. 20:09 *🧠 Understanding Knowledge Storage in Large Language Models* - Large language models (LLMs) store knowledge in their parameters. - Parameters in LLMs are essential for tasks like text-to-image generation. - Comparison between the parameter size of stable diffusion and GPT-3. 22:19 *📚 Role of Knowledge Graphs in Text Generation* - Questioning the necessity of vast parameter sizes in LLMs for text generation. - Introducing knowledge graphs as efficient knowledge extraction mechanisms. - Using knowledge graphs to store, curate, and extract valuable information. 23:15 *💡 Significance of Knowledge in a World of LLMs* - Emphasizing the value of knowledge in a world of infinite content generation. - Utilizing LLMs for knowledge extraction and symbolic representation. - Highlighting the importance of overfitting for truth in symbolic systems. 25:12 *🌐 Extending the Expressivity of Knowledge Graphs* - Discussing the limitations of knowledge graphs in terms of expressivity. - Introducing initiatives like Wikipedia Functions to enhance expressivity. - Proposing the introduction of a new special value, "it's complicated," in knowledge graphs. 26:50 *🚀 Enhancing the Future with Knowledge Graphs and LLMs* - LLMs have limitations including hallucinations, expense, and difficulty in auditing. - Knowledge graphs can address these limitations and provide ground truth for LLMs. - The future of knowledge graphs is promising, especially in conjunction with LLMs. 30:08 *💰 Cost Consideration in Knowledge Extraction* - Comparing the cost-effectiveness of using LLMs versus knowledge graphs for answering questions. - Considering whether cost consciousness will impact the hype around LLMs. - Money is a significant factor influencing the adoption and sustainability of LLMs. Made with HARPA AI

Decentralized knowledge graphs deserve more attention.

You should also mention that WordLift does not work with any standard non-WordPress websites, which is very very limiting.

Please, could someone give me some tips about enabling the option "clone from wikidata" used in 28:55, in my local wikibase instance or in wikibase cloud?

22:00: Yes, that's really where KG's would be optimal when integrated into an LLM -- trivia / facts that can't be reduced further than nodes and links in a KG. I mean if you think about the modelling horsepower that would remain in a 170B ANN after outsourcing fact learning and retrieval would be insane.

Great survey and talk, thanks Sir

Very good overview of the data disaster that describes how many/most organizations managed their data. Was intrigued by the Knowledge Graph as a solution in the modern data architecture stack, but really need a lot more detail on what using a knowledge graph means to the business users (search, discovery, inference) and the technical work to develop and maintain these ontologies (RDF/OWL). Creating enterprise ontologies for data is not trivial and organizing the multiple ontology domains into a knowledge graph is a steep curve for most data teams.

Really nice presentation. Finally a talk that explains the basic vocabulary for the semantic web clearly and gives practical guidance on how to approach and structure an ontology project.

metaphysical time travel or make-believe? why not both! :D but seriously amazing of you to play a more perfect information game - cheers!

Really make sense!

‘’it’s complicated”, love it

*think back, think forward*

Subscribed the moment I saw this was a channel on knowledge graphs XD

Very useful! Q: Do you see that when the Google SGE fully rolls out - that it may influenece this?

"Promo sm" 😃

Fast forward to 2:30 for better audio.

I subscribed to your UA-cam channel, your content is very good, but SEO needs to be done

This is very interesting do you have a link to a scientific paper where there are technical details?

i think a book needed named "knowledge graph in practice". not any cms or web framework uses these approaches!!!. I follow topic knowledge graph for 10 years. This concept is very close to being referred to as a buzz word. every new conference or book offers theoretical examples. Now it is necessary to provide practical examples. Let me explain why I made such a harsh comment. If we do not provide practical examples, someone will ignore some theoretical steps and develop a general useable method and application. then another 30 years but we say this is not a knowledge graph. We have experienced this on the web.

Would be nice if you published the chat

very good and important, aperfect direction of technology. True demonstration of blockchain usage