AWS Machine Learning Blog

NOVEMBER 1, 2024

Fine-tuning is a powerful approach in natural language processing (NLP) and generative AI , allowing businesses to tailor pre-trained large language models (LLMs) for specific tasks. This process involves updating the model’s weights to improve its performance on targeted applications. Sonnet across various tasks.

LLM 92

LLM Prompt Engineer Prompt Engineering Generative AI 92

Artificial Corner

JULY 30, 2023

Natural Language Processing (NLP) is a subfield of artificial intelligence. Machine translation, summarization, ticket categorization, and spell-checking are among the examples. Prompts design is a process of creating prompts which are the instructions and context that are given to Large Language Models to achieve the desired task.

Large Language Models 98

Large Language Models LLM Natural Language Processing Deep Learning 98

AWS Machine Learning Blog

MAY 7, 2024

This post walks through examples of building information extraction use cases by combining LLMs with prompt engineering and frameworks such as LangChain. Prompt engineering Prompt engineering enables you to instruct LLMs to generate suggestions, explanations, or completions of text in an interactive way.

Prompt Engineering 117

Prompt Engineering Prompt Engineer Large Language Models LLM 117

AWS Machine Learning Blog

OCTOBER 6, 2023

For instance, in ecommerce, image-to-text can automate product categorization based on images, enhancing search efficiency and accuracy. With millions of products listed, effective sorting and categorization poses a significant challenge. This is where the power of auto-tagging and attribute generation comes into its own.

Generative AI 119

Generative AI Prompt Engineer Prompt Engineering Computer Vision 119

AWS Machine Learning Blog

SEPTEMBER 14, 2023

Amazon Comprehend is a natural-language processing (NLP) service that uses machine learning to uncover valuable insights and connections in text. Knowledge management – Categorizing documents in a systematic way helps to organize an organization’s knowledge base. Amazon Comprehend custom classification can be useful in this situation.

Categorization 116

Categorization Machine Learning Data Scientist Natural Language Processing 116

Explosion

MAY 17, 2023

But if you’re working on the same sort of Natural Language Processing (NLP) problems that businesses have been trying to solve for a long time, what’s the best way to use them? We want to aggregate it, link it, filter it, categorize it, generate it and correct it. We want to recommend people text based on other text they liked.

LLM 135

LLM NLP Large Language Models OpenAI 135

AWS Machine Learning Blog

MARCH 13, 2024

Use LLM prompt engineering to accommodate customized policies The pre-trained Toxicity Detection models from Amazon Transcribe and Amazon Comprehend provide a broad toxicity taxonomy, commonly used by social platforms for moderating user-generated content in audio and text formats.

Natural Language Processing 129

Natural Language Processing LLM Prompt Engineer Prompt Engineering 129

AWS Machine Learning Blog

OCTOBER 24, 2023

Amazon Comprehend is a natural language processing (NLP) service that uses ML to extract insights from text. When a new document type introduced in the IDP pipeline needs classification, the LLM can process text and categorize the document given a set of classes. You can also fine-tune them for specific document classes.

IDP 133

IDP LLM Prompt Engineer Prompt Engineering 133

AWS Machine Learning Blog

SEPTEMBER 1, 2023

Operationalization journey per generative AI user type To simplify the description of the processes, we need to categorize the main generative AI user types, as shown in the following figure. They have deep end-to-end ML and natural language processing (NLP) expertise and data science skills, and massive data labeler and editor teams.

Generative AI 123

Generative AI Prompt Engineer Prompt Engineering ML 123

Unite.AI

AUGUST 4, 2023

In this article, we will delve deeper into these issues, exploring the advanced techniques of prompt engineering with Langchain, offering clear explanations, practical examples, and step-by-step instructions on how to implement them. Prompts play a crucial role in steering the behavior of a model.

Prompt Engineering 245

Prompt Engineering Prompt Engineer Python NLP 245

ODSC - Open Data Science

OCTOBER 27, 2023

The core idea behind this phase is automating the categorization or classification using AI. We use Amazon Textract’s document extraction abilities with LangChain to get the text from the document and then use prompt engineering to identify the possible document category.

IDP 98

IDP LLM Large Language Models Data Science 98

ODSC - Open Data Science

JANUARY 7, 2025

Natural Language Processing (NLP) has emerged as a dominant area, with tasks like sentiment analysis, machine translation, and chatbot development leading the way. Classification techniques, such as image recognition and document categorization, remain essential for a wide range of industries.

Data Scientist 40

Data Scientist Data Science Deep Learning Machine Learning 40

AWS Machine Learning Blog

DECEMBER 5, 2023

The custom metadata helps organizations and enterprises categorize information in their preferred way. His focus area is AI/ML, and he helps customers with generative AI, large language models, and prompt engineering. For example, metadata can be used for filtering and searching.

Metadata 119

Metadata Auto-classification Auto-complete Content Enrichment 119

Snorkel AI

AUGUST 17, 2023

Users can easily constrain an LLM’s output with clever prompt engineering. That minimizes the chance that the prompt will overrun the context window, and also reduces the cost of high-volume runs. Its categorical power is brittle. The former will make the generative model’s outputs (mostly) fall into an expected range.

Generative AI 52

Generative AI BERT LLM Prompt Engineer 52

Snorkel AI

JUNE 23, 2023

This approach was less popular among our attendees from the wealthiest of corporations, who expressed similar levels of interest in fine-tuning with prompts and responses, fine-tuning with unstructured data, and prompt engineering.

Data Science 52

Data Science Large Language Models Machine Learning Categorization 52

Heartbeat

FEBRUARY 13, 2024

Broad Streams of LLM Applications Though LLM applications are vast, we can broadly categorize the LLM applications into the following streams: Prompt Engineering: This is the most basic and widely applicable one. Here, we primarily work with proprietary LLMs such as ChatGPT.

Data Scientist 52

Data Scientist LLM Deep Learning Explainability 52

Snorkel AI

MAY 25, 2023

At its debut, BERT shattered the records for a suite of NLP benchmark tests. Within a short time, BERT became the standard tool for NLP tasks. From 2018 to the modern day, NLP researchers have engaged in a steady march toward ever-larger models. This is generally known as “prompt programming” or “prompt engineering.”

Large Language Models 52

Large Language Models BERT Neural Network LLM 52

Snorkel AI

MAY 25, 2023

At its debut, BERT shattered the records for a suite of NLP benchmark tests. Within a short time, BERT became the standard tool for NLP tasks. From 2018 to the modern day, NLP researchers have engaged in a steady march toward ever-larger models. This is generally known as “prompt programming” or “prompt engineering.”

Large Language Models 52

Large Language Models BERT Neural Network LLM 52

deepsense.ai

NOVEMBER 14, 2023

In short, EDS is the problem of the widespread lack of a rational approach to and methodology for the objective, automated and quantitative evaluation of performance in terms of generative model finetuning and prompt engineering for specific downstream GenAI tasks related to practical business applications. There is a ‘but’, however.

Generative AI 111

Generative AI ML Prompt Engineer Prompt Engineering 111

Snorkel AI

DECEMBER 14, 2023

In the image above, you can see on the left that categorical “overlap” is sometimes intentional. Many organizations pursue model-centric iteration, such as hyper-parameter tuning and prompt engineering. During task formulation, the customer wanted to use an existing taxonomy for categorizing and labeling videos.

Categorization 52

Categorization Data Scientist Prompt Engineer Prompt Engineering 52

Unite.AI

SEPTEMBER 20, 2023

Transformers in NLP In 2017, Cornell University published an influential paper that introduced transformers. These are deep learning models used in NLP. Hugging Face , started in 2016, aims to make NLP models accessible to everyone. This discovery fueled the development of large language models like ChatGPT.

LLM 341

LLM NLP BERT Python 341

Unite.AI

AUGUST 8, 2023

LaMDA Google 173 billion Not Open Source, No API or Download Trained on dialogue could learn to talk about virtually anything MT-NLG Nvidia/Microsoft 530 billion API Access by application Utilizes transformer-based Megatron architecture for various NLP tasks. How Are LLMs Used? However, relying on a single attention mechanism can be limiting.

Generative AI 243

Generative AI ChatGPT Neural Network Convolutional Neural Networks 243

Flipboard

DECEMBER 6, 2023

Types of summarizations There are several techniques to summarize text, which are broadly categorized into two main approaches: extractive and abstractive summarization. Extractive summarization Extractive summarization is a technique used in NLP and text analysis to create a summary by extracting key sentences.

BERT 167

BERT Large Language Models Artificial Intelligence Artificial Intelligence 167

AWS Machine Learning Blog

NOVEMBER 1, 2023

Key strengths of VLP include the effective utilization of pre-trained VLMs and LLMs, enabling zero-shot or few-shot predictions without necessitating task-specific modifications, and categorizing images from a broad spectrum through casual multi-round dialogues.

Auto-classification 114

Auto-classification LLM Auto-complete Generative AI 114

ODSC - Open Data Science

MARCH 21, 2025

Led by Dwayne Natwick , CEO of Captain Hyperscaler, LLC, and a Microsoft Certified Trainer (MCT) Regional Lead & Microsoft Most Valuable Professional (MVP) , these sessions will provide practical insights and hands-on experience in prompt engineering and generative AI development.

Prompt Engineering 52

Prompt Engineering Prompt Engineer OpenAI Generative AI 52

AWS Machine Learning Blog

JANUARY 7, 2025

Traditional NLP pipelines and ML classification models Traditional natural language processing pipelines struggle with email complexity due to their reliance on rigid rules and poor handling of language variations, making them impractical for dynamic client communications. However, not all of them were effective for Parameta.

Generative AI 100

Generative AI Automation Data Extraction ETL 100