spaCy (@spacy_io) / Twitter

Pinned Tweet

Today we're releasing spaCy v3.0! 🛸 Transformer-based pipelines for SOTA models ⚙️ New training and config system 🧬 Models using any framework 🪐 Manage end-to-end workflows 🔥 New and improved APIs, components & more

github.com

Release v3.0.0: Transformer-based pipelines, new training system, project templates, custom models,...

NEW: Want to make the transition from spaCy v2 to spaCy v3 as smooth as possible for you and your organization? We're now offering commercial migration support for your spaCy pipelines! We...

15

270

822

Use spaCy as AWS Lambda layers! (by

@keithrozario

) Lambda layers are a convenient way to package libraries and other dependencies to run your code in the

@awscloud

without provisioning or managing servers. github.com/keithrozario/K

2

15

87

This Python Applied NLP tutorial will teach you use

@jaidevd

's Numerizer with

@spacy_io

and build a

@streamlit

app that's deployed for Free on

@huggingface

Spaces - A new project to your portfolio 🤗 Tutorial youtube.com/watch?v=DpVt1W #100DaysOfCode #NLProc

2

20

63

Use spaCy as AWS Lambda layers! (by

@keithrozario

) Lambda layers are a convenient way to package libraries and other dependencies to run your code in the

@awscloud

without provisioning or managing servers. github.com/keithrozario/K

2

15

87

Out now: spaCy v3.2.1! 🧼 New 'doc_cleaner' component: remove doc.tensor, doc._._trf_data or other temporary attributes to reduce the size of output docs 🔬 New Matcher pattern attributes 🎉 And more improvements and bug fixes! Release notes:

github.com

Release v3.2.1: doc_cleaner component, new Matcher attributes, bug fixes and more · explosion/spaCy

New features and improvements NEW: doc_cleaner component for removing doc.tensor,doc._._trf_data or other Doc attributes at the end of the pipeline to reduce size of output docs. NEW: ENT_ID and...

11

52

spaCy

@spacy_io

Dec 7

Out now: spaCy v3.2.1! 🧼 New 'doc_cleaner' component: remove doc.tensor, doc._._trf_data or other temporary attributes to reduce the size of output docs 🔬 New Matcher pattern attributes 🎉 And more improvements and bug fixes! Release notes:

github.com

Release v3.2.1: doc_cleaner component, new Matcher attributes, bug fixes and more · explosion/spaCy

New features and improvements NEW: doc_cleaner component for removing doc.tensor,doc._._trf_data or other Doc attributes at the end of the pipeline to reduce size of output docs. NEW: ENT_ID and...

11

52

New release: textacy v0.12! Extend the core functionality of spaCy with textacy (by

@bjdewilde

) This release includes: 🧮 More text statistics functionality 📃 Improved doc extensions handling 📦 Better packaging github.com/chartbeat-labs

18

88

spaCy

@spacy_io

Dec 7

New release: textacy v0.12! Extend the core functionality of spaCy with textacy (by

@bjdewilde

) This release includes: 🧮 More text statistics functionality 📃 Improved doc extensions handling 📦 Better packaging github.com/chartbeat-labs

18

88

Did you know that agglutinative languages like Finnish and Korean get a decent performance boost with floret? 🌸 floret combines fastText's subwords with Bloom embeddings for compact full-coverage vectors! Demos github.com/explosion/proj

github.com

GitHub - explosion/floret:

fastText + Bloom embeddings for compact, full-coverage vectors with...

fastText + Bloom embeddings for compact, full-coverage vectors with spaCy - GitHub - explosion/floret:

fastText + Bloom embeddings for compact, full-coverage vectors with spaCy

3

8

53

spaCy

@spacy_io

Dec 1

Did you know that agglutinative languages like Finnish and Korean get a decent performance boost with floret? 🌸 floret combines fastText's subwords with Bloom embeddings for compact full-coverage vectors! Demos github.com/explosion/proj

github.com

GitHub - explosion/floret:

fastText + Bloom embeddings for compact, full-coverage vectors with...

fastText + Bloom embeddings for compact, full-coverage vectors with spaCy - GitHub - explosion/floret:

fastText + Bloom embeddings for compact, full-coverage vectors with spaCy

3

8

53

🎙 🍵Live AMA w

: I'm super stoked to host Ines tomorrow, join us for a live AMA around

@spacy_io

,

@explosion_ai

, and beyond! 📍wandb.me/ama-ines-monta

9

46

Wow!

v3 is a brilliant case study for #python software architecture design. The way they structure "projects" could be an ML build tool in it's own right. The packaging and distribution of models is genius too.

youtube.com

SPACY v3: State-of-the-art NLP from Prototype to Production

2

14

77

🏺 Use spaCy to analyze a low resource language like Ancient Greek! Check this Space on

@huggingface

🤗 huggingface.co/spaces/Jacobo/

3

36

157

Great article in

on how they're using

and prodi.gy to indentify quotes in text ✨ I especially like the focus on designing annotation schemes to deal with ambiguity in language – it's why iteration is SO important! theguardian.com/info/2021/nov/

2

43

240

🏺 Use spaCy to analyze a low resource language like Ancient Greek! Check this Space on

@huggingface

🤗 huggingface.co/spaces/Jacobo/

3

36

157

New: Experimental edit tree lemmatizer that posts accuracies above 95% for many languages! 🌳 It learns to predict lemmatization rules from a corpus of examples and removes the need to write an exhaustive set of per-language lemmatization rules. explosion.ai/blog/edit-tree

3

42

165

spaCy

@spacy_io

Nov 24

New: Experimental edit tree lemmatizer that posts accuracies above 95% for many languages! 🌳 It learns to predict lemmatization rules from a corpus of examples and removes the need to write an exhaustive set of per-language lemmatization rules. explosion.ai/blog/edit-tree

3

42

165

📚 BookNLP is a natural language processing pipeline that scales to books and other long documents Feature highlight 👸🤴 Character name clustering & coref resolution: "Tom", "Tom Sawyer", "Mr. Sawyer", "Thomas Sawyer" all become "TOM_SAWYER"!

@dbamman

github.com/booknlp/booknlp

GIF

3

63

264

🌸 floret: fastText + Bloom embeddings for compact, full-coverage vectors with spaCy! floret combines: 👟 fastText's subwords to provide embeddings for any word ⚡ Bloom embeddings ("hashing trick") for a compact vector table pip install floret github.com/explosion/flor

20

121

spaCy

@spacy_io

Nov 23

📚 BookNLP is a natural language processing pipeline that scales to books and other long documents Feature highlight 👸🤴 Character name clustering & coref resolution: "Tom", "Tom Sawyer", "Mr. Sawyer", "Thomas Sawyer" all become "TOM_SAWYER"!

@dbamman

github.com/booknlp/booknlp

GIF

3

63

264

Nov	DEC	Jan
	09
2020	2021	2022

spaCy’s Tweets