NLP | Towards Data Science https://towardsdatascience.com/tag/nlp/ Publish AI, ML & data-science insights to a global community of data professionals. Mon, 14 Jul 2025 23:44:33 +0000 en-US hourly 1 https://wordpress.org/?v=6.8.1 https://towardsdatascience.com/wp-content/uploads/2025/02/cropped-Favicon-32x32.png NLP | Towards Data Science https://towardsdatascience.com/tag/nlp/ 32 32 Topic Model Labelling with LLMs https://towardsdatascience.com/topic-model-labelling-with-llms/ Mon, 14 Jul 2025 23:44:18 +0000 https://towardsdatascience.com/?p=606581 Python tutorial for reproducible labeling of cutting-edge topic models with GPT4-o-mini.

The post Topic Model Labelling with LLMs appeared first on Towards Data Science.

]]> Reinforcement Learning from Human Feedback, Explained Simply https://towardsdatascience.com/explained-simply-reinforcement-learning-from-human-feedback/ Mon, 23 Jun 2025 23:31:07 +0000 https://towardsdatascience.com/?p=606394 The one technique that made ChatGPT so smart

The post Reinforcement Learning from Human Feedback, Explained Simply appeared first on Towards Data Science.

]]> Build an AI Agent to Explore Your Data Catalog with Natural Language https://towardsdatascience.com/build-and-ai-agent-to-explore-your-data-catalog-with-natural-language/ Mon, 16 Jun 2025 17:37:42 +0000 https://towardsdatascience.com/?p=606309 Leverage LLMs to query your Databricks Data Catalog

The post Build an AI Agent to Explore Your Data Catalog with Natural Language appeared first on Towards Data Science.

]]> A Practical Guide to BERTopic for Transformer-Based Topic Modeling https://towardsdatascience.com/a-practical-guide-to-bertopic-for-transformer-based-topic-modeling/ Thu, 08 May 2025 05:08:43 +0000 https://towardsdatascience.com/?p=605946 A deep dive into BERTopic’s 6 modules to transform financial news into insightful topics

The post A Practical Guide to BERTopic for Transformer-Based Topic Modeling appeared first on Towards Data Science.

]]> Roadmap to Becoming a Data Scientist, Part 4: Advanced Machine Learning https://towardsdatascience.com/roadmap-to-becoming-a-data-scientist-part-4-advanced-machine-learning/ Fri, 14 Feb 2025 17:00:00 +0000 https://towardsdatascience.com/?p=597896 Introduction Data science is undoubtedly one of the most fascinating fields today. Following significant breakthroughs in machine learning about a decade ago, data science has surged in popularity within the tech community. Each year, we witness increasingly powerful tools that once seemed unimaginable. Innovations such as the Transformer architecture, ChatGPT, the Retrieval-Augmented Generation (RAG) framework, and state-of-the-art computer vision models — including GANs — have […]

The post Roadmap to Becoming a Data Scientist, Part 4: Advanced Machine Learning appeared first on Towards Data Science.

]]> Show and Tell https://towardsdatascience.com/show-and-tell-e1a1142456e2/ Mon, 03 Feb 2025 16:30:24 +0000 https://towardsdatascience.com/show-and-tell-e1a1142456e2/ Implementing one of the earliest neural image caption generator models with PyTorch.

The post Show and Tell appeared first on Towards Data Science.

]]> NLP Illustrated, Part 3: Word2Vec https://towardsdatascience.com/nlp-illustrated-part-3-word2vec-5b2e12b6a63b/ Wed, 29 Jan 2025 17:01:57 +0000 https://towardsdatascience.com/nlp-illustrated-part-3-word2vec-5b2e12b6a63b/ An exhaustive and illustrated guide to Word2Vec with code!

The post NLP Illustrated, Part 3: Word2Vec appeared first on Towards Data Science.

]]> Topic Modelling in Business Intelligence: FASTopic and BERTopic in Code https://towardsdatascience.com/topic-modelling-in-business-intelligence-fastopic-and-bertopic-in-code-2d3949260a37/ Wed, 22 Jan 2025 18:02:13 +0000 https://towardsdatascience.com/topic-modelling-in-business-intelligence-fastopic-and-bertopic-in-code-2d3949260a37/ A comparison of two cutting-edge dynamic topic models solving consumer complaints classification exercise

The post Topic Modelling in Business Intelligence: FASTopic and BERTopic in Code appeared first on Towards Data Science.

]]> How to Evaluate LLM Summarization https://towardsdatascience.com/how-to-evaluate-llm-summarization-18a040c3905d/ Wed, 22 Jan 2025 17:37:07 +0000 https://towardsdatascience.com/how-to-evaluate-llm-summarization-18a040c3905d/ A practical and effective guide for evaluating AI summaries

The post How to Evaluate LLM Summarization appeared first on Towards Data Science.

]]> Data-Driven Decision Making with Sentiment Analysis in R https://towardsdatascience.com/data-driven-decision-making-with-sentiment-analysis-in-r-3d4a3b19a0db/ Tue, 21 Jan 2025 19:06:30 +0000 https://towardsdatascience.com/data-driven-decision-making-with-sentiment-analysis-in-r-3d4a3b19a0db/ Leveraging the Quanteda, Textstem and Sentimentr Packages to Extract Customer Insights and Enhance Business Strategy

The post Data-Driven Decision Making with Sentiment Analysis in R appeared first on Towards Data Science.

]]> Understanding the Evolution of ChatGPT: Part 3- Insights from Codex and InstructGPT https://towardsdatascience.com/understanding-the-evolution-of-chatgpt-part-3-insights-from-codex-and-instructgpt-04ece2967bf7/ Tue, 21 Jan 2025 18:19:27 +0000 https://towardsdatascience.com/understanding-the-evolution-of-chatgpt-part-3-insights-from-codex-and-instructgpt-04ece2967bf7/ Mastering the art of fine-tuning: Learnings for training your own LLMs.

The post Understanding the Evolution of ChatGPT: Part 3- Insights from Codex and InstructGPT appeared first on Towards Data Science.

]]> Contextual Topic Modelling in Chinese Corpora with KeyNMF https://towardsdatascience.com/contextual-topic-modelling-in-chinese-corpora-with-keynmf-9a1d02f02648/ Mon, 13 Jan 2025 18:47:24 +0000 https://towardsdatascience.com/contextual-topic-modelling-in-chinese-corpora-with-keynmf-9a1d02f02648/ A comprehensive guide on getting the most out of your Chinese topic models, from preprocessing to interpretation.

The post Contextual Topic Modelling in Chinese Corpora with KeyNMF appeared first on Towards Data Science.

]]> Understanding the Evolution of ChatGPT: Part 2 – GPT-2 and GPT-3 https://towardsdatascience.com/understanding-the-evolution-of-chatgpt-part-2-gpt-2-and-gpt-3-77a01ed934c5/ Mon, 13 Jan 2025 13:02:06 +0000 https://towardsdatascience.com/understanding-the-evolution-of-chatgpt-part-2-gpt-2-and-gpt-3-77a01ed934c5/ Scaling from 117M to 175B: Insights into GPT-2 and GPT-3.

The post Understanding the Evolution of ChatGPT: Part 2 – GPT-2 and GPT-3 appeared first on Towards Data Science.

]]> What Would a Stoic Do? – An AI-Based Decision-Making Model https://towardsdatascience.com/what-would-a-stoic-do-an-ai-based-decision-making-model-df01c86b7348/ Sun, 12 Jan 2025 13:31:58 +0000 https://towardsdatascience.com/what-would-a-stoic-do-an-ai-based-decision-making-model-df01c86b7348/ Using AI to build Marcus Aurelius' reincarnation

The post What Would a Stoic Do? – An AI-Based Decision-Making Model appeared first on Towards Data Science.

]]> Linearizing Llama https://towardsdatascience.com/linearizing-llama-ef7266d03050/ Fri, 10 Jan 2025 12:01:58 +0000 https://towardsdatascience.com/linearizing-llama-ef7266d03050/ Speeding Up Llama: A Hybrid Approach to Attention Mechanisms

The post Linearizing Llama appeared first on Towards Data Science.

]]> Understanding the Evolution of ChatGPT: Part 1-An In-Depth Look at GPT-1 and What Inspired It https://towardsdatascience.com/understanding-the-evolution-of-gpt-part-1-an-in-depth-look-at-gpt-1-and-what-inspired-it-b7388a32e87d/ Mon, 06 Jan 2025 18:13:46 +0000 https://towardsdatascience.com/understanding-the-evolution-of-gpt-part-1-an-in-depth-look-at-gpt-1-and-what-inspired-it-b7388a32e87d/ Tracing the roots of ChatGPT: GPT-1, the foundation of OpenAI's LLMs

The post Understanding the Evolution of ChatGPT: Part 1-An In-Depth Look at GPT-1 and What Inspired It appeared first on Towards Data Science.

]]> Meet GPT, The Decoder-Only Transformer https://towardsdatascience.com/meet-gpt-the-decoder-only-transformer-12f4a7918b36/ Mon, 06 Jan 2025 17:01:43 +0000 https://towardsdatascience.com/meet-gpt-the-decoder-only-transformer-12f4a7918b36/ Understanding and implementing the GPT-1, GPT-2 and GPT-3 architectures

The post Meet GPT, The Decoder-Only Transformer appeared first on Towards Data Science.

]]> Is Complex Writing Nothing But Formulas? https://towardsdatascience.com/is-complex-writing-nothing-but-formulas-289e0a33793f/ Fri, 13 Dec 2024 18:33:19 +0000 https://towardsdatascience.com/is-complex-writing-nothing-but-formulas-289e0a33793f/ Text analytics hints at how volumes of writing get created

The post Is Complex Writing Nothing But Formulas? appeared first on Towards Data Science.

]]> AI, My Holiday Elf: Building a Gift Recommender for the Perfect Christmas https://towardsdatascience.com/ai-my-holiday-elf-building-a-gift-recommender-for-the-perfect-christmas-caf163d38e10/ Sun, 08 Dec 2024 14:32:13 +0000 https://towardsdatascience.com/ai-my-holiday-elf-building-a-gift-recommender-for-the-perfect-christmas-caf163d38e10/ How I used AI and Streamlit to create a festive and fun gift recommendation app

The post AI, My Holiday Elf: Building a Gift Recommender for the Perfect Christmas appeared first on Towards Data Science.

]]> NLP Illustrated, Part 1: Text Encoding https://towardsdatascience.com/nlp-illustrated-part-1-text-encoding-41ba06c0f512/ Tue, 19 Nov 2024 13:01:57 +0000 https://towardsdatascience.com/nlp-illustrated-part-1-text-encoding-41ba06c0f512/ An illustrated guide to text-to-number translation, with code

The post NLP Illustrated, Part 1: Text Encoding appeared first on Towards Data Science.

]]>