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

Project

• spaCy
• Prodigy
• Ellf
• Thinc
• Consulting
• Case Study

Topics

• LLMs
• NLP Strategy
• Annotation
• Biomedical
• Finance
• Media
• Legal
• Humanities
• Computer Vision

Category

• Blog
• Release
• Universe
• Talk
• Interview
• Video
• Paper
• Book

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

Streaming spaCy

Join spaCy author and core developer Matt as he works on the library, develops features and fixes bugs, while chatting about all things NLP and open source. Every Thursday at 2pm CET and Friday at 11am CET.

🔮 thinc v9.0.0 Apr 19, 2024 \Better learning rate schedules and integration of thinc-apple-ops

🔮 thinc v8.2.0 Aug 11, 2023 \Updates for automatic imports

Implementing a custom trainable component for relation extraction

Relation extraction refers to the process of predicting and labeling semantic relationships between named entities. In this blog post, we'll go over the process of building a custom relation extraction component using spaCy and Thinc. We'll also add a Hugging Face transformer to improve performance at the end of the post. You'll see how you can utilize Thinc's flexible and customizable system to build an NLP pipeline for biomedical relation extraction.

Fast transformer inference with Metal Performance Shaders

We are happy to introduce support for Metal Performance Shaders in Thinc PyTorch layers. This makes it possible to run spaCy transformer-based pipelines on GPU on Apple Silicon Macs and improves inference speed up to 4.7 times.

🍏 thinc-apple-ops v0.1.0 Jul 19, 2022 \Many performance improvements

spaCy v3: Custom trainable relation extraction component

spaCy v3.0 features new transformer-based pipelines that get spaCy’s accuracy right up to the current state-of-the-art, and a new training config and workflow system to help you take projects from prototype to production. In this video, Sofie shows you how to apply all these new features when implementing a custom trainable component from scratch.