Explosion in 2022: Our Year in Review
Summary
Explosion, a company in the NLP space, announced significant product advancements in its 2022 year in review. Key developments include the introduction of a new end-to-end neural coreference resolution component for its spaCy library, enhancing its capabilities for complex text understanding. The company also achieved a substantial speed improvement, boosting its Convolutional Neural Network (CNN) pipelines by up to 60%. Furthermore, Explosion expanded its linguistic support by publishing new pre-trained spaCy pipelines for Finnish, Korean, Swedish, and Croatian. Complementing these updates, the Prodigy annotation tool received several enhancements, including new recipes designed to facilitate annotation workflows using zero-shot or few-shot learning techniques.
Key takeaway
For NLP Engineers evaluating toolkits, Explosion's 2022 updates to spaCy and Prodigy offer significant enhancements. You should consider integrating the new neural coreference component for deeper text analysis and leveraging the 60% faster CNN pipelines for improved processing efficiency. Explore the new pre-trained pipelines for Finnish, Korean, Swedish, and Croatian to expand your multilingual project capabilities. Additionally, utilize Prodigy's zero-shot and few-shot learning recipes to accelerate your data annotation efforts.
Key insights
Explosion significantly enhanced its NLP tools, spaCy and Prodigy, in 2022 with new components, speed, and language support.
In practice
- Integrate neural coref for advanced text understanding.
- Utilize faster CNN pipelines for efficiency.
- Apply zero-shot recipes for rapid annotation.
Topics
- spaCy
- Prodigy
- Neural Coreference
- CNN Pipelines
- Zero-shot Learning
- Multilingual NLP
Best for: NLP Engineer, Machine Learning Engineer, AI Engineer
Related on 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.