Explosion builds developer tools for AI, Machine Learning and Natural Language Processing. →

Project

Topics

Category

Tasks

Select...Code Generation, Coreference Resolution, Dependency Parsing, Distillation, Embeddings & Vectors, Entity Linking, Evaluation, Image Classification, Image Segmentation, Layout Analysis, Lemmatization, Named Entity Recognition, Object Detection, Optical Character Recognition (OCR), Part-of-Speech Tagging, PII Anonymization, Question Answering, Relation Extraction, Retrieval-Augmented Generation (RAG), Rule-Based Matching, Span Categorization, Text Classification, Text Generation, Tokenization, Weak Supervision

Authors

Select...Adriane Boyd, Ákos Kádár, Basile Dura, Chung-Fan Tsai, Damian Romero, Daniel de Kok, Duygu Altinok, Edward Schmuhl, Helena Steckmeister, India Kerle, Ines Montani, Kabir Khan, Lj Miranda, Madeesh Kannan, Magdalena Anioł, Matthew Honnibal, Paul O’Leary McCann, Peter Baumgartner, Philip Vollet, Raphael Mitsch, Rehan Ahmed, Richard Hudson, Ryan Wesslen, Sofie Van Landeghem, Victoria Slocum, Vincent D. Warmerdam, Vinit Ravishankar, Walter Henry

Back to our roots: Company update and future plans

We’re back to running Explosion as a smaller, independent-minded and self-sufficient company. spaCy and Prodigy will stay stable and sustainable, maintained by their original authors. We’ll keep updating our stack with the latest technologies, without changing its core identity or purpose.

A practical guide to human-in-the-loop distillation

This blog post presents practical solutions for using the latest state-of-the-art models in real-world applications and distilling their knowledge into smaller and faster components that you can run and maintain in-house.

Simply Simplify Language

Interactive app by the Canton of Zurich, Switzerland, using LLMs and spaCy to analyze and simplify institutional communication and make bureaucratic German more inclusive.

ZenML v0.58.0

New out-of-the-box Prodigy integration in ZenML for LLMs and beyond, to make data development and annotation a core part of your MLOps lifecycle.

The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs

With the latest advancements in NLP and LLMs, and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big tech monopolies?

How S&P Global is making markets more transparent with NLP, spaCy and Prodigy

A case study on S&P Global’s efficient information extraction pipelines for real-time commodities trading insights in a high-security environment.

Half hour of labeling power: Can we beat GPT?

Large Language Models (LLMs) offer a lot of value for modern NLP and can typically achieve surprisingly good accuracy on predictive NLP tasks. But can we do even better than that? In this workshop we show how to use LLMs at development time to create high-quality datasets and train specific, smaller, private and more accurate models for your business problems.

The AI Revolution Will Not Be Monopolized

Open-source initiatives are pivotal in democratizing AI technology, offering transparent, extensible tools that empower users. Daniel Dominguez summarizes the key takeaways from Ines’ recent talk for InfoQ.

Muted: Multilingual Targeted Offensive Speech Identification and Visualization

Muted can leverage any transformer-based HAP-classification model to identify toxic spans, without further fine-tuning. In addition, we use the spaCy library to identify the specific targets and arguments for the words predicted by the attention heatmaps.

Prodigy in 2023: LLMs, task routers, QA and plugins

We have made a ton of new updates in Prodigy this year with v1.12, v1.13, and v1.14 releases. So we decided to write a post about them.