TΞCHnical Terrence’s Post

On my reading stack: A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks (a tip of the hat to Raphaël MANSUY, for his recent post citing this paper) https://lnkd.in/gYMh9b5B

7 Steps to Mastering Large Language Model Fine-tuning From theory to practice, learn how to enhance your NLP projects with these 7 simple steps.

🚀 Excited to Share My Latest Article! 🚀 I've just published my second article, "Evolution of Language Representation Techniques: A Journey from BoW to GPT" on Medium! In this piece, I explore the fascinating world of language representation techniques and take a deep dive into key topics: 1️⃣ What is a Language Representation and Vectorization Technique? 2️⃣ Different Types of Language Representations 3️⃣ What is an Embedding? 4️⃣ Difference between Word2Vec, BERT, and GPT Approaches Working on this article has been an incredible learning experience and has greatly enriched my journey as a GenAI intern. Analyzing the evolution of these techniques has deepened my understanding of NLP and enhanced my skills in using modern language models. Special thanks to my mentor Kanav Bansal sir and Innomatics Research Labs for their guidance and support throughout this journey! 🙏✨ If you're interested in understanding how language models like Word2Vec, BERT, and GPT have transformed NLP, I’d love for you to give it a read and share your thoughts! 📖💬 Here's my article link in Medium: https://lnkd.in/g8MnDJTx If you like the content in the article, Do follow 😀. #GenAI #NaturalLanguageProcessing #LanguageModels #Word2Vec #BERT #GPT

EleutherAI Presents Language Model Evaluation Harness (lm-eval) for Reproducible and Rigorous NLP Assessments, Enhancing Language Model Evaluation

"Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective" #AffectiveComputing #LargeLanguageModels #InstructionTuning #PromptEngineering https://lnkd.in/duERXbSD

🌟 Milestone Achieved: My Second Medium Article is Live! 🌟  I'm ecstatic to share another significant step in my learning journey – publishing my second article on Medium titled "The Evolution of Language Representation Techniques: From BoW to GPT"🚀  Language representation in NLP has come a long way, evolving from simple, rule-based methods to advanced, context-aware models like GPT. In this article, I delve into:   ✅ A timeline of major breakthroughs in language representation   ✅ Simplified explanations of techniques like BoW, TF-IDF, Word Embeddings, and Transformers   ✅ How each milestone has shaped modern NLP systems  This guide reflects my passion for understanding complex ideas and breaking them down into digestible insights for everyone. Whether you're a curious learner or an NLP enthusiast, there's a takeaway for you!   This is a part of my work during my internship at Innomatics Research Labs. A special thank you to Kanav Bansal sir for this guidance and support through out this journey. 🔗 *Read it here:* https://lnkd.in/gi-7hX_3 I’d love to hear your feedback and thoughts! Let’s discuss how these advancements have impacted the way we interact with technology and each other.  #NaturalLanguageProcessing #MediumPublication #AI #NLP #LearningJourney #GrowthMindset #KnowledgeSharing #NLP #AI #DataScience #Word2Vec #BERT #GPT #GenAI

Calls: Fifth Celtic Language Technology Workshop 2025: Call for Papers: We invite submissions of original contributions on resources, theories, systems, applications, and methods in Natural Language Processing for any of the Celtic languages. Topics of interest include, but are not limited to the following: Knowledge-based NLP/ Neural NLP/Hybrid approaches to processing Celtic Languages Fine-Tuning of Pre-Trained Language Models (PLM) Experiments and Evaluations (Prompting and Fine-Tuning) of Large Languages Model (LLMs) Evaluating Celtic Language

The videos from PyConDE & PyData Berlin are out!  Check out my talk on Monolingual, Multilingual, and Cross-lingual Text Classification in April 2024 😉

This article by Anna Rogers highlights how the term "emergence" is used in different contexts within NLP. It questions whether these properties truly exist in large language models. Read more now! #LLM

I'm starting a series called "Demystifying NLP: From Text to Embeddings" on Towards Data Science. This series will provide an overview of text representation in modern NLP, progressing from basic concepts to more advanced techniques, and will include practical, hands-on examples. In my first article, "The Art of Tokenization: Breaking Down Text for AI", I explain how tokenization works in NLP and discuss various tokenization algorithms, including Byte-Pair Encoding. https://lnkd.in/d6NyFQXW #NLP #tokenization #machinelearning #AI