Recently we published an article “Memory enhances ChatGPT performance in multi-hop QA”. The article discusses the approach for ChatGPT memory augmentation and compares it to the task-tuned language model on multi-hop QA tasks.
We are excited to announce our new article about #multitask models in #DeepPavlov. These models allow combining many tasks into one backbone while retaining or even increasing the model quality.
We are excited to announce the DeepPavlov release 1.3.0:
◾️few-shot text classification model that allows you to operate with a small amount of training data
◾️refactored ODQA model optimized to consume less RAM during training
◾️ long-anticipated syntax parser and morphotagger
📣 TIME FOR NEXT TUTORIAL ON DREAM!
Discover how to create a generative bot 🤖 with a predefined persona, using the existing Dream ☁️ Persona distribution that utilizes OpenAI ChatGPT.
#AI#NLP#DeepPavlov#GenerativeAI
https://t.co/6RVyWF6g7f
NLP field is highly dynamic, and with the current pace of change we’d like to hear from you to learn how else we could help you solve your everyday NLP tasks; if you’re up for it, we’d highly appreciate your filling out a short survey!
https://t.co/n0chzgbNCd
We are back with some fantastic news 🔥: a brand new demo of #DeepPavlov 🎅Library just came out, featuring a lot of new, much needed #multilingual 🤖models.
Be the first to try it out and don’t hesitate to share your feedback with us!
https://t.co/wBrPYKDxGp
📣 TUTORIALS ON DREAM
Learn how to create a simple and light-weight 🤖 that specializes in discussing movies and answering factoid questions, utilizing the existing Dream ☁️ components.
#AI#NLP#DeepPavlov#GenerativeAI
https://t.co/WTy3YSs0PR
\4 More links
Dream web-site https://t.co/M1guwjekCY
DeepPavlov Discord https://t.co/ZS6rX68YLg
List of available Guides https://t.co/enW8xN7sxE
Dream FAQ https://t.co/mBiFIe5C10
\2 Discover how our platform prioritizes efficiency, modularity, scalability, and extensibility, making it easier to develop complex dialog systems from scratch. Explore our rich library of NLP components and learn how to create scalable, industrial-grade AI assistants. 🛠️📚
📣 Calling all #ACL2023 attendees! 🚀 Don't miss our System Demo on the open-source DeepPavlov Dream, designed for building complex, generative AI Assistants. 🤖💬
10 July @ 14:00
Demo Session 2 @ Frontenac Ballroom, Queens Quay&Bay
🧵
#AI#NLP#DeepPavlov#GenerativeAI
Ever wondered how #ChatGPT stacks up against traditional NLP models? 🤔 The results might surprise you! 🚀 Dive into this insightful analysis to discover the strengths and weaknesses of ChatGPT on Q&A tasks. Will it outshine the rest? 🌟 #NLProc#AI https://t.co/zgCc3Uo7Kw
2M tokens may not be enough to create a complete personality, but it's a start. The possibility of a job as a synthetic personality designer is exciting - let's see how many more tokens we need to unlock it! Stay tuned for more updates
Now the question is: can you build a complete personality with 2M tokens?
If yes:
Job of the future: synthetic personality designer.
If no:
How many more tokens are necessary?
Grammarly has announced GrammarlyGO, a collection of generative AI writing and editing tools that serve as a productivity aid for communication. This expands on the spelling, grammar, and style guidance already offered by the company's apps and plug-ins.
https://t.co/UOyzIYaRm7