Using spaCy with Hugging Face Transformers

2019-10-12 · 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

Integrating Transformer models, such as BERT from Hugging Face, with the spaCy framework now enables their application in production NLP. While these advanced models have established new accuracy benchmarks across almost every NLP leaderboard, their nascent software ecosystem has primarily focused on research opportunities rather than immediate production deployment. Matt's talk details how to leverage these powerful models within spaCy to address real-world problems, emphasizing the significant potential of transfer learning for practical NLP solutions. This integration bridges the gap between advanced research and deployable systems, offering a pathway for practitioners to utilize high-performing models in their daily workflows, regardless of their specific software package preferences.

Key takeaway

For NLP Engineers seeking to deploy advanced models, integrating Hugging Face Transformers with spaCy offers a direct path to production. You can now leverage models like BERT for real-world problems, overcoming the research-centric nature of their native ecosystems. This approach allows you to build highly accurate NLP systems using transfer learning, significantly enhancing your project's performance and deployability.

Key insights

Integrate Hugging Face Transformers with spaCy for production-ready NLP applications using transfer learning.

Principles

• Transformer models set new NLP accuracy standards.
• Research-focused ecosystems need production bridges.
• Transfer learning enables practical NLP.

Method

The content describes how to use Transformer models in spaCy for real problems, leveraging transfer learning for production NLP.

In practice

• Apply BERT-like models in spaCy.
• Develop production NLP systems.
• Utilize transfer learning for efficiency.

Topics

• spaCy
• Hugging Face Transformers
• BERT
• Natural Language Processing
• Transfer Learning
• Production NLP

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

Related on AIssential

• spaCy meets Transformers: Fine-tune BERT, XLNet and GPT-2 — spaCy now integrates Hugging Face Transformers (BERT, GPT-2, XLNet) for enhanced NLP accuracy.
• The PR you would have opened yourself — A new Skill and test harness streamline porting transformer models to MLX, addressing agent-generated PR quality.
• Fine-Tuning BERT for Sentiment Analysis: A Beginner-Friendly Guide — Fine-tuning pre-trained transformer models like BERT enables high-accuracy NLP tasks with minimal training data.
• spaCy v3: Custom trainable relation extraction component — spaCy v3 enables custom trainable components and Transformer integration for significant NLP performance gains.
• ggml.ai joins Hugging Face to ensure the long-term progress of Local AI — The ggml.ai and Hugging Face collaboration aims to standardize and simplify local AI model deployment and user experience.
• Transfer Learning in Machine Learning and Deep Learning — Transfer learning reuses pre-trained model knowledge to accelerate new task learning with less 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.