Explosion

JANUARY 31, 2021

? Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy - Release v1.0.0: Rewrite for spaCy v3, Transformer component and TransformerListener, plus more functions · explosion/spacy-transformers

40

40

Explosion

JANUARY 29, 2023

It's been another exciting year at Explosion! We've developed a new end-to-end neural coref component for spaCy, improved the speed of our CNN pipelines up to 60%, and published new pre-trained pipelines for Finnish, Korean, Swedish and Croatian.

40

40

Explosion

APRIL 2, 2023

The default Bloom embedding layer in spaCy is unconventional, but very powerful and efficient. Now we have released the first technical report by Explosion, where we explain Bloom embeddings in more detail and rigorously compare them to traditional embeddings.

40

40

Explosion

JANUARY 29, 2023

It’s been another exciting year at Explosion! We’ve developed a new end-to-end neural coref component for spaCy , improved the speed of our CNN pipelines up to 60%, and published new pre-trained pipelines for Finnish, Korean, Swedish and Croatian. New spaCy pipeline components As part of our spaCy v3.3 Happy reading!

Python 59

Python Data Scientist Machine Learning Machine Learning 59

Explosion

SEPTEMBER 1, 2021

Since founding Explosion in 2016, we’ve run the company as a profitable business. This stable platform has helped spaCy grow to one of Python’s most popular open-source projects. We’ve funded spaCy from sales of our annotation tool Prodigy , which we’ve now sold to over 500 companies, with thousands of customers in total.

52

52

Explosion

JUNE 22, 2020

? spaCy building blocks and visualizers for Streamlit apps - GitHub - explosion/spacy-streamlit: ? spaCy building blocks and visualizers for Streamlit apps

40

40

Explosion

FEBRUARY 7, 2022

Explosion is pleased to announce a new development services offering, spaCy Tailored Pipelines. We’ll build you a custom natural language processing pipeline, delivered in a standardized format using spaCy’s projects system.

Natural Language Processing 40

Natural Language Processing 40

Heartbeat

APRIL 23, 2023

Developing a chatbot can be a complex task, but with the help of SpaCy, it can be made easier. In this article, we will explore how to develop a chatbot using the SpaCy NLP library. What is SpaCy? Train the SpaCy model: The next step is to train the SpaCy model using the preprocessed training data.

Natural Language Processing 52

Natural Language Processing Machine Learning Machine Learning Deep Learning 52

Explosion

DECEMBER 28, 2019

We’re also very happy to see our team grow this year, with four new members working under the Explosion umbrella: Sofie Van Landeghem , Adriane Boyd, Walter Henry and Sebastián Ramírez. It also included a small glimpse of spaCy, Prodigy and our day-to-day work on GitHub. ? Mar 9: Ever been curious about how Explosion makes its money?

Machine Learning 52

Machine Learning Machine Learning Python Natural Language Processing 52

Explosion

DECEMBER 30, 2020

While 2020 hasn’t been easy for anyone, at Explosion we’ve considered ourselves relatively fortunate in this most interesting year. Feb 8: At PyCon Colombia, Ines was also interviewed by Karolina Ladino and they talked the history of spaCy, and how to get into programming, machine learning and NLP. Special thanks to Yohei Tamura ! ?

Python 52

Python Machine Learning Machine Learning Natural Language Processing 52

Explosion

NOVEMBER 16, 2021

spaCy v3, with its configuration and project system, introduced a way to solve this problem. I’ve been using spaCy for a few years now, as I did a lot of NLP projects both during my studies and previous work. Back then, when I wanted to train my own NER model using spaCy v2, I’d write my own training loop.

Machine Learning 52

Machine Learning Machine Learning Python Data Preparation 52

Explosion

OCTOBER 1, 2019

of the spaCy Natural Language Processing library is leaner, cleaner and even more user-friendly. New models and data augmentation spaCy v2.2 If you’re using the spacy train command , the new data augmentation strategy can be enabled with the new --orth-variant-level parameter. Version 2.2 German model. We’ve set it to 0.3

Algorithm 59

Algorithm Natural Language Processing Python Data Science 59

Explosion

JANUARY 12, 2018

We founded Explosion in October 2016, so this was our first full calendar year in operation. spaCy In 2017 spaCy grew into one of the most popular open-source libraries for Artificial Intelligence. Some statistics: Published 18 spaCy releases and another 19 alphas. spaCy’s Machine Learning library for NLP in Python.

Machine Learning 52

Machine Learning Machine Learning Supervised Learning Python 52

Explosion

DECEMBER 14, 2021

Read about the journey of developing Healthsea, an end-to-end spaCy pipeline for analyzing user reviews to supplementary products and extracting their potential effects on health. ? I’m a machine learning engineer at Explosion, and together with our fantastic team , we’ve been working on Healthsea to further expand the spaCy universe ?.

Clustering 52

Clustering Machine Learning Machine Learning Natural Language Processing 52

Ines Montani

OCTOBER 2, 2016

Today, we launched the website for our new company, Explosion AI. Explosion is a digital studio specialising in Artificial Intelligence and Natural Language Processing. The Past It all started when my partner, Matt , asked me to develop a simple website for his newly launched software library, spaCy.

AI 52

AI AI Natural Language Processing Artificial Intelligence 52

Ines Montani

MAY 9, 2017

In this post I’ll share some lessons we’ve learned from running spaCy , the popular and fast-growing library for Natural Language Processing in Python. A case for centralised, commercial open-source In many ways, spaCy is a pretty typical commercial open-source project. spaCy’s strength is that it’s easy to use, fast and opinionated.

Natural Language Processing 52

Natural Language Processing Deep Learning Deep Learning Python 52

Explosion

AUGUST 3, 2017

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!). Most of those insights have been used to make spaCy better: AI DevOps was hard, so we made sure models could be installed via pip.

Supervised Learning 52

Supervised Learning Python Machine Learning Machine Learning 52

Explosion

OCTOBER 2, 2016

We’re launching Explosion AI to give you a better option. For the last two years, we’ve been developing spaCy , one of the leading NLP libraries. Matt left academia to write spaCy in 2014. Now dozens of companies are using spaCy in production, in combination with the rest of Python’s awesome open-source ecosystem.

AI 40

AI AI Machine Learning Machine Learning 40

Explosion

FEBRUARY 15, 2023

Cheyanne Baird, NLP Research Scientist for Posh Technologies In a recent interview, Explosion talked with Cheyanne Baird , NLP Research Scientist at Posh, and discussed why Posh chose Prodigy for their annotation needs. There's too many options.' When I was looking at Prodigy I liked it because you could customize it. Try the live demo!

Data Scientist 59

Data Scientist Natural Language Processing AI AI 59

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 Supervised Learning Artificial Intelligence Artificial Intelligence 52

Ines Montani

FEBRUARY 8, 2017

I forgot about his advice until years later, when I found myself doing exactly that, helping computers understand language, which eventually led to founding my first company, Explosion AI. I started working with Matt , who had just released spaCy , an open-source library for Natural Language Processing.

Natural Language Processing 52

Natural Language Processing Computer Science Computer Science AI 52

Explosion

APRIL 1, 2017

This topic is something we’re continuing to work on at Explosion. Transfer learning and better annotation tooling are both key to our current plans for spaCy and related projects. spaCy uses roughly the same algorithm, just with a few more features, and an additional trick to reduce over-fitting (parameter averaging).

Supervised Learning 40

Supervised Learning Machine Learning Machine Learning Algorithm 40

ML Review

MARCH 5, 2019

The common bigrams (“deep_learning”) and trigrams (“convolutional_neural_networks”) are what we’d like to learn embeddings for but there is an issue due to combinatorial explosion when creating n-grams. “a”, “the”, “of”) and tokens that appear less than a threshold amount of times (e.g. 5 or 30 — different for each method).

AI 52

AI AI Support Vector Machines Natural Language Processing 52