spaCy/website/docs/usage/facts-figures.md

3.9 KiB
Raw Blame History

title teaser next menu
Facts & Figures The hard numbers for spaCy and how it compares to other tools /usage/spacy-101
Feature Comparison
comparison
Benchmarks
benchmarks

Comparison

When should I use spaCy?

  • I'm a beginner and just getting started with NLP. spaCy makes it easy to get started and comes with extensive documentation, including a beginner-friendly 101 guide, a free interactive online course and a range of video tutorials.
  • I want to build an end-to-end production application. spaCy is specifically designed for production use and lets you build and train powerful NLP pipelines and package them for easy deployment.
  • I want my application to be efficient on GPU and CPU. While spaCy lets you train modern NLP models that are best run on GPU, it also offers CPU-optimized pipelines, which are less accurate but much cheaper to run.
  • I want to try out different neural network architectures for NLP. spaCy lets you customize and swap out the model architectures powering its components, and implement your own using a framework like PyTorch or TensorFlow. The declarative configuration system makes it easy to mix and match functions and keep track of your hyperparameters to make sure your experiments are reproducible.
  • I want to build a language generation application. spaCy's focus is natural language processing and extracting information from large volumes of text. While you can use it to help you re-write existing text, it doesn't include any specific functionality for language generation tasks.
  • I want to research machine learning algorithms. spaCy is built on the latest research, but it's not a research library. If your goal is to write papers and run benchmarks, spaCy is probably not a good choice. However, you can use it to make the results of your research easily available for others to use, e.g. via a custom spaCy component.

Benchmarks

spaCy v3.0 introduces transformer-based pipelines that bring spaCy's accuracy right up to current state-of-the-art. You can also use a CPU-optimized pipeline, which is less accurate but much cheaper to run.

Evaluation details

  • OntoNotes 5.0: spaCy's English models are trained on this corpus, as it's several times larger than other English treebanks. However, most systems do not report accuracies on it.
  • Penn Treebank: The "classic" parsing evaluation for research. However, it's quite far removed from actual usage: it uses sentences with gold-standard segmentation and tokenization, from a pretty specific type of text (articles from a single newspaper, 1984-1989).

import Benchmarks from 'usage/_benchmarks-models.md'

Dependency Parsing System UAS LAS
spaCy RoBERTa (2020)1 95.5 94.3
spaCy CNN (2020)1
Mrini et al. (2019) 97.4 96.3
Zhou and Zhao (2019) 97.2 95.7

Dependency parsing accuracy on the Penn Treebank. See NLP-progress for more results. **1. ** Project template: benchmarks/parsing_penn_treebank.