Introducing spaCy v3.0

2021-02-01 · Source: Explosion · Developer tools and consulting for AI, Machine Learning and NLP - Explosion.ai · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

spaCy v3.0 marks a substantial release, introducing new transformer-based pipelines that significantly boost its accuracy to align with current state-of-the-art performance in natural language processing. A key addition is a new workflow system, specifically designed to guide projects seamlessly from initial prototyping phases through to full production deployment. This version also simplifies pipeline configuration and training processes, making it more accessible for developers. Furthermore, spaCy v3.0 includes numerous new and improved integrations, enhancing its compatibility and utility within the wider NLP ecosystem. These updates collectively aim to provide a more powerful, efficient, and user-friendly framework for advanced NLP applications.

Key takeaway

For NLP Engineers considering an upgrade or starting new projects, spaCy v3.0 offers significant advantages. You should prioritize adopting this version to leverage its state-of-the-art transformer pipelines for enhanced accuracy. The new workflow system will streamline your project development from prototyping to production, making configuration and training much more efficient. Explore its improved integrations to optimize your existing NLP ecosystem.

Key insights

spaCy v3.0 achieves state-of-the-art NLP accuracy via transformer pipelines and streamlines project workflows from prototype to production.

Method

A new workflow system helps take projects from prototype to production, simplifying pipeline configuration and training.

In practice

• Utilize transformer-based pipelines for higher accuracy.
• Leverage the workflow system for project management.
• Explore new integrations with NLP tools.

Topics

• spaCy v3.0
• Transformer Pipelines
• NLP Workflows
• Model Training
• Ecosystem Integration

Best for: AI Engineer, NLP Engineer, Machine Learning Engineer, MLOps Engineer

Related on AIssential

• spaCy v3: State-of-the-art NLP from Prototype to Production — spaCy v3 streamlines production NLP with transformer integration, robust configuration, and structured project management.
• State-of-the-Art Transformer Pipelines in spaCy — spaCy offers robust, configurable Transformer pipelines for NLP tasks, often outperforming LLMs on predictive tasks with modest data.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Explosion · Developer tools and consulting for AI, Machine Learning and NLP - Explosion.ai.