Ines Montani

AUGUST 4, 2017

I’m excited and proud to finally share what we’ve been working on since launching Explosion AI , alongside our NLP library spaCy and our consulting projects. Prodigy is a project very dear to my heart and seeing it come to life has been one of the most exciting experiences as a software developer so far.

Python 52

Python Software Development Data Scientist Artificial Intelligence 52

Explosion

AUGUST 3, 2017

That’s why we’re pleased to introduce Prodigy , a downloadable tool for radically efficient machine teaching. We’ve been working on Prodigy since we first launched Explosion last year, alongside our open-source NLP library spaCy and our consulting projects (it’s been a busy year!).

Convolutional Neural Networks 52

Convolutional Neural Networks Python Machine Learning Algorithm 52

Towards AI

FEBRUARY 23, 2024

DALL·E 3 DALL-E DALL-E 3, the AI ​​artistic prodigy, can generate hyper-realistic visions, from a cat astronaut exploring coral reefs to a Van Gogh-style portrait. Professional Quality: It meets the requirements of professional projects in terms of resolution, details, and customization.

AI 109

AI AI ChatGPT Algorithm 109

Explosion

AUGUST 4, 2017

Prodigy is a project very dear to my heart and seeing it come to life has been one of the most exciting experiences as a software developer so far.

Software Development 52

Software Development 52

Explosion

APRIL 27, 2023

Like the video, some of the code has been simplified for this post, but you can find the full project in our projects repo. spaCy projects are easy to set up on your own; you can check out the README and project.yaml for instructions on how to get started! We will use an example spaCy project that runs the full workflow.

NLP 69

NLP Neural Network Machine Learning Deep Learning 69

Explosion

OCTOBER 2, 2016

In December we were pleased to release our first commercial product, our annotation tool Prodigy. Unfortunately, this means we’re not currently available for new consulting projects. This sort of structure is a poor fit for most software projects, where taking the measurements is harder than making the suit.

Machine Learning 40

Machine Learning AI AI NLP 40

John Snow Labs

MAY 24, 2023

Likewise, almost 80% of AI/ML projects stall at some stage before deployment. Streamlining text annotation is a difficult task as it comes with certain obstacles that impact the success of an AI project. Below are some features of Prodigy: – It is suitable for novice users.

Natural Language Processing 52

Natural Language Processing NLP Machine Learning Auto-classification 52

Mlearning.ai

JUNE 29, 2023

Its prodigious capabilities empower developers and researchers alike to delve into a vast array of NLP tasks with unparalleled dexterity. Text Preprocessing with CORENLP Text preprocessing is a crucial step in any NLP project, as it helps in transforming raw text data into a format suitable for machine learning algorithms.

NLP 52

NLP Machine Learning Natural Language Processing Algorithm 52

Explosion

AUGUST 1, 2019

Your project should already have access to a process that has human-level natural language understanding capabilities, at the expense of high run-time cost and high latency: manual annotation. We’re especially looking forward to rolling out support for these transformer models in our annotation tool Prodigy.

BERT 52

BERT NLP Neural Network Categorization 52

Explosion

DECEMBER 28, 2019

In the interview, Matt and Ines talked about Prodigy , where training corpora come from and the challenges of annotating data for an NLP system – with some ideas about how to make it easier. ? It also included a small glimpse of spaCy, Prodigy and our day-to-day work on GitHub. ? ✨ Feb 18: Finally in February, Prodigy v1.7.0

NLP 52

NLP BERT Machine Learning Python 52

Explosion

DECEMBER 30, 2020

Mar 16: Ines published an end-to-end video tutorial showing how to use our annotation tool Prodigy to train a named entity recognition model from scratch, by taking advantage of semi-automatic annotation and modern transfer learning techniques. ? We’ve been using it extensively in our projects ever since! ? Also: cats! ? ?

NLP 52

NLP Python Machine Learning Natural Language Processing 52

Explosion

DECEMBER 14, 2021

The complete spaCy project can be found on GitHub and includes all training data, components, and workflows. Healthsea Codebase spaCy v3 project with all training data and workflows ? Healthsea is an experimental project and the results should not be used as a foundation for solving health problems. Segmentation component 2.1

NLP 52

NLP Machine Learning Natural Language Processing Computer Vision 52

Explosion

NOVEMBER 21, 2019

In this post, we present a new version of the library, new vectors, new evaluation recipes, and a demo NER project that we trained to usable accuracy in just a few hours. We then used Prodigy to quickly annotate training and evaluation data, which we then combine with spaCy’s transfer-learning functionality to train a model that achieves 82.1%

NLP 52

NLP Convolutional Neural Networks Neural Network Natural Language Processing 52

Explosion

MAY 17, 2023

This generative output could be a complete game-changer, finally delivering the “insights” that data science projects have generally over-promised and under-delivered. Here’s how I think LLMs should be used in NLP projects today — an approach I would call LLM pragmatism. Prodigy v1.12 But should you?

LLM 135

LLM NLP Large Language Models OpenAI 135

Explosion

JANUARY 12, 2018

Funded 120% of company and personal expenses through consulting projects. Prodigy In December we released Prodigy , our new annotation tool powered by active learning. Prodigy is our first commercial product, and the first product of its type on the market. Released Prodigy v1.0, in addition to five beta versions.

NLP 52

NLP Neural Network Machine Learning Python 52

Explosion

APRIL 1, 2017

We wrote this post while working on Prodigy , our new annotation tool for radically efficient machine teaching. Prodigy features many of the ideas and solutions for data collection and supervised learning outlined in this blog post. Try Prodigy! The above graphic shows an annotation project using this active learning approach.

Algorithm 40

Algorithm Machine Learning Deep Learning Python 40

Explosion

JULY 6, 2021

The upcoming version of our annotation tool Prodigy (currently available as a pre-release for all users) will also feature a new workflow and UI for annotating overlapping and nested spans, which you can use to create training data for spaCy’s SpanCategorizer component. skweak Toolkit for weak supervision applied to NLP tasks ?

BERT 52

BERT Auto-complete NLP Python 52

Explosion

JUNE 15, 2020

You can find the code and data in our growing projects repository. The series lets you sit beside Vincent as he works through an example data science project using spaCy. We also have a big release of our annotation tool Prodigy pretty much ready to go. update (giving you all the new models), Prodigy v1.10

Natural Language Processing 52

Natural Language Processing NLP Explainability Machine Learning 52

ODSC - Open Data Science

OCTOBER 6, 2023

This means you can reuse code blocks for different projects, streamlining the development process and increasing efficiency. It’s akin to a flight data recorder for your AI projects — everything gets noted, leaving no room for ambiguity. This is a significant consideration for projects that require real-time responsiveness.

Prompt Engineer 52

Prompt Engineer Prompt Engineering Python Data Science 52

Explosion

MARCH 17, 2019

Prodigy is a fully scriptable annotation tool that complements spaCy extremely well. Most NLP projects are easier if you have a way to train models on exactly your data. The formats are fully compatible, so you’ll be able to use your Prodigy patterns with the entity ruler, and vice versa. average was 2 lbs.")

NLP 52

NLP Python Neural Network Natural Language Processing 52

Explosion

NOVEMBER 9, 2016

You can now also create training and evaluation data for these models with Prodigy , our new active learning-powered annotation tool. See this video for an example of training an NER system using Prodigy. The Australian equivalent of the SEC funded a project to crawl Australian websites and automatically detect financial scams.

Deep Learning 52

Deep Learning NLP Convolutional Neural Networks Neural Network 52

Explosion

JANUARY 31, 2021

It features new transformer-based pipelines that get spaCy’s accuracy right up to the current state-of-the-art, and a new workflow system to help you take projects from prototype to production. Project template: benchmarks/ner_conll03. spaCy v3.0 is a huge release! Stanza (StanfordNLP) 1 88.8 Flair 2 89.7 and CoNLL-2003 corpora.

NLP 52

NLP Python BERT Auto-classification 52