Exciting News! Presenting our latest work: 'Aspect-level Sentiment Analysis Dataset for Therapies on Twitter' 🌐🔄 Unlock insights into public sentiment surrounding therapies. Download now: sciencedirect.com/science/articl… #Research #SentimentAnalysis 🚀

In addition to prompting LLMs, many developers are now also experimenting with fine-tuning. I describe in The Batch how to choose from the growing menu of options for building applications with LLMs: Prompting, few-shot, fine-tuning, pre-training. deeplearning.ai/the-batch/issu…

We just released 'Large Language Models with Semantic Search”, built with cohere, and taught by Jay Alammar and Luis Serrano 🇵🇸🍉. Search is a key part of many applications. Say, you need to retrieve documents or products in response to a user query; how can LLMs help? You’ll

A very unique textbook 'Information theory, inference and learning algorithms' by Sir MacKay combining Information Theory with Machine Learning.

Nicely written!

Book PDF freely available at:
👉inference.org.uk/itila/book.html

A cheat sheet explanation of how Large Language Models work:

Thrilled to share that I'm starting my career as an Assistant Professor Emory BMI with a secondary appointment in the Department of Gynecology and Obstetrics and Global Health Emory University!

How to Extract Text from Any PDF and Image for Large Language Model by Zoumana buff.ly/3Y4H1XL

I needed this animation when I started learning PyTorch.

If you are just starting your PyTorch journey, bookmark this:

If you are interested in reviewing research on alignment for LLMs, look no further.

This new survey paper covers different aspects of alignment research such as data collection, training methodologies, and model evaluation.

Aligning LLMs with human expectations is an active

Twitter's new API pricing (and related mess) is causing so much headache for us!
If you are an academic researcher working with Twitter data, how are you dealing with the changes?
#AcademicTwitter

Excited and grateful to have my recent publication acknowledged by my advisor Abeed Sarker, PhD! Thank you for your support and guidance throughout this research journey.

New paper alert (on JAHA): 'Text Classification System Detects Fontan Patients in Electronic Records With Higher Accuracy Than ICD Codes' | Journal of the American Heart Association ... (congrats Yuting Guo) ahajournals.org/doi/10.1161/JA…

Great presentation by Jeanne Powell at the #aime2023 session on NLP.
Emory BMI

New paper out. My student Jeanne Powell will be presenting this work at AIME

'Classification of Fall Types in Parkinson's Disease from Self-report Data Using Natural Language Processing'

link.springer.com/chapter/10.100…

A few EM/Tox physicians from Europe have come up to me at #EAPCCT2023 and said they keep an eye out for drug supply trends in the US to know what they are going to have to deal with in a few years from now #xylazine

I’m honored to have been selected as a Student Travel Award recipient to present my work on fall classification using NLP at the 21st International Conference on Artificial Intelligence in Medicine!

Thank you to coauthors Yuting Guo, Abeed Sarker, PhD, and J Lucas McKay PhD MSCR (he/him)!!

Explore the world of social media NLP with #SocBERT - our pretrained model designed for analyzing social media text. Discover new insights and boost performance. Check out our latest paper to learn more! #NLP #LLM

paper: aclanthology.org/2023.insights-…

model: huggingface.co/sarkerlab/SocB…

Very nice course!

“Transformers from scratch” by Brandon Rohrer 🤖

This is one of the best write ups, that starts from 0 and explains every single detail of the model architecture.

Even if you need a refresher or don’t, I would still highly recommend reading it:

e2eml.school/transformers.h…