Ines Montani

Selected Talks

About Me

Hi, I’m Ines.

I’m a software developer working on Artificial Intelligence and Natural Language Processing technologies, and the co-founder and CEO of Explosion. We’re the makers of spaCy, one of the leading open-source libraries for Natural Language Processing in Python, and Prodigy, a modern annotation tool for creating training data for machine learning models.

I believe in programming until four in the morning in my pyjamas instead of getting up early to attend conferences about productivity. I believe in making the best possible products instead of launching just for the sake of it because some startup advice blog told me so. I believe in rational planning, logical consequences and bullshit-free hard work instead of “following my dreams”. In short, I believe in doing things.

I grew up on the internet and started coding and designing websites at 11. After completing my degree in Communication Science, Media Studies and Linguistics, I spent four years working in media and sales, before founding Explosion. I live in Berlin and I occasionally speak at conferences and make videos. In 2020, I became a Fellow of the Python Software Foundation.

I’ve been featured in…

c’t Magazin · it-daily · l’Opinion · IEEE Spectrum · Berliner Zeitung · GitHub Newsletter · InfoQ #1, #2, #3 · TalkPython #504, #465, #351, #300, #297, #202 · Python Bytes #191, #139 · Vanishing Gradients · Learning From Machine Learning · Software Engineering Radio · Leading With Data · The Python Show · Teaching Python · KDnuggets 2021, 2020, 2019 · Rasa Chats · Snorkel ScienceTalks · Gradient Dissent · DevJourney · Practical AI · ZenML Pipeline Conversations · Console DevTools · Byte Into IT · SourceSort · Python-Podcast.de · UNMUTE IT · TVP3 · Bayerischer Rundfunk · kulturnews · Zündfunk (Bayern 2) · Techtiefen · Mouse vs. Python · DataHack Radio · TWiML & AI · ARD-alpha · connect professional · NLP Highlights · Spiegel Online · The Exponential View · O’Reilly Newsletter

I’ve given talks at…

PyCon Germany · PyCon India · PyCon Colombia · PyCon Italy · PyCon Lithuania · PyCon France · PyCon Ireland · PyCon+Web · PyData London · PyData NYC · PyData Amsterdam · EuroPython · EuroSciPy · QCon · InfoQ Dev Summit · dotAI · DataHack Summit · InfoShare · Zündfunk Netzkongress · NAACL · Humboldt University Berlin · Princeton University · and more

© Eugene Hyland
© Ema Discordant
© Eugene Hyland

Blog & Updates

Vibe NLP for Applied NLP
PyCon DE & PyData

Vibe NLP for Applied NLP

What if we could take learnings from AI-powered coding agents and apply them to solving real-world NLP problems? In this talk, I’ll show how we’ve built a powerful virtual NLP assistant to help developers create practical and modular solutions that are small, fast and fully data-private.
Darmstadt, Germany
Building AI with AI
PyCon Ireland

Building AI with AI

AI-powered coding assistants have transformed the way we build software, and AI itself. In this talk, I show why we should use LLMs to build systems instead of as systems, and why code is more important than ever, not less.
Dublin, Ireland
How AI reshapes IT skills
connect professional

How AI reshapes IT skills

German article featuring my take on what AI means for IT professionals.
Despite the economic downturn: opportunities for IT specialists
c’t Magazin

Despite the economic downturn: opportunities for IT specialists

I was interviewed for this German article on the future of technology jobs and what’s needed for innovation and AI.
AI in Reality Fireside Chat: Enterprise AI & Open-Source Innovation
PyCon DE & PyData

AI in Reality Fireside Chat: Enterprise AI & Open-Source Innovation

Panel discussion with Alexander CS Hendorf, Dr. Alexander Beck, Walid Mehanna and me.
Darmstadt, Germany
Making beautiful slides for your talks, part 5: Sharing your presentations

Making beautiful slides for your talks, part 5: Sharing your presentations

What’s next, now that you’ve given a successful presentation with beautiful slides? For part 5, I’ve collected tips for how to share your slides with the world.
design 5 minute read
KI zwischen Freiheit und Kontrolle: The AI Revolution Will Not Be Monopolized
data:unplugged

KI zwischen Freiheit und Kontrolle: The AI Revolution Will Not Be Monopolized

Münster, Germany
How Love Without Sound helps the music industry recover millions in revenue for artists with NLP, spaCy and Prodigy

How Love Without Sound helps the music industry recover millions in revenue for artists with NLP, spaCy and Prodigy

A case study on Love Without Sound’s innovative AI-powered tools for the music industry and law firms specializing in royalty negotiations.
tech
What the history of the web can teach us about the future of AI
PyCon+Web keynote

What the history of the web can teach us about the future of AI

Berlin, Germany
PyLadies entrepreneurs and career development
PyLadiesCon

PyLadies entrepreneurs and career development

Reality is not an End-to-End Prediction Problem: Applied NLP in the Age of Generative AI
dotAI

Reality is not an End-to-End Prediction Problem: Applied NLP in the Age of Generative AI

Paris, France
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
InfoQ Dev Summit

Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation

Munich, Germany
Beautiful Slides for Beginners
EuroSciPy lightning talk

Beautiful Slides for Beginners

Szczecin, Poland
The NLP and AI Revolution with the spaCy Creators
Vanishing Gradients podcast

The NLP and AI Revolution with the spaCy Creators

interview
New Prodigy website

New Prodigy website

I’ve revamped the Prodigy website and docs to include more examples, features and real-world industry use cases.
news
A practical guide to human-in-the-loop distillation

A practical guide to human-in-the-loop distillation

tech
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
PyData London

Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation

LLMs have enormous potential, but also challenge existing workflows in industry that require modularity, transparency and data privacy. In this talk, I'll show practical solutions for using the latest models and distilling their knowledge into smaller and faster components that you can run and maintain in-house.
London, UK
Episode #465: The AI Revolution Won't Be Monopolized
TalkPython podcast

Episode #465: The AI Revolution Won't Be Monopolized

interview
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
PyCon DE & PyData Berlin

The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs

With the latest advancements in NLP and LLMs, and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big tech monopolies? I don’t think so, and in this talk, I’ll show you why.
Berlin, Germany
Ines Montani on Natural Language Processing
Software Engineering Radio

Ines Montani on Natural Language Processing

We cover generative vs. predictive tasks, creating a pipeline and breaking down problems, labeling examples for training, fine-tuning models, using LLMs to label data and build prototypes, and the spaCy NLP library.
interview
A beginner’s guide to making beautiful slides for your talks

A beginner’s guide to making beautiful slides for your talks

I love designing slides for my talks, so here are some of my not-so-secret secrets and three beginner-friendly steps for how you can up your slides game.
design 8 minute read
spaCy 101 Zine Book

spaCy 101 Zine Book

My 30-page zine about spaCy is now available in our merch store as a pocketbook with free PDF and stickers!
design
The Python Show Podcast

Natural Language Processing and Python

interview
Large Language Models: From Prototype to Production
EuroPython keynote

Large Language Models: From Prototype to Production

Prague, Czech Republic
Incorporating LLMs into practical NLP workflows
PyCon DE

Incorporating LLMs into practical NLP workflows

Berlin, Germany
AI/ML for the rest of us
GitHub Newsletter

AI/ML for the rest of us

interview
Evolution of spaCy

Evolution of spaCy

interview
Pipeline Conversations

Creating Tools that Spark Joy

interview
Applied NLP Thinking: How to Translate Problems into Solutions

Applied NLP Thinking: How to Translate Problems into Solutions

We’ve been running Explosion for about five years now, which has given us a lot of insights into what NLP looks like in industry contexts. In this blog post, I discuss some of the biggest challenges for applied NLP and translating business problems into ML solutions.
opinion
python-podcast.de

Natural Language Processing mit spaCy

interview
spaCy v3.0

spaCy v3.0

spaCy v3.0 is a huge release! It features new transformer-based pipelines that get spaCy’s accuracy right up to the current state-of-the-art, and a new workflow system to help you take projects from prototype to production.
code
Rasa Chats podcast

Building Resilient NLP Applications

interview
DevJourney podcast

Episode #122: Ines Montani brought linguistic and computers together

interview
Prodigy v1.10: Dependencies, relations, audio, video & more

Prodigy v1.10: Dependencies, relations, audio, video & more

code
Speaker Interview
PyCon Colombia

Speaker Interview

Karo and I talked about getting into tech and machine learning, and what's next for spaCy and our other tools.
interview Medellìn, Colombia
Practical AI podcast

Modern NLP with spaCy

interview
Künstliche Intelligenz beyond the hype
Zündfunk Netzkongress

Künstliche Intelligenz beyond the hype

Munich, Germany
Let Them Write Code
PyCon India keynote

Let Them Write Code

Chennai, India
spaCy and Explosion: past, present and future

spaCy and Explosion: past, present and future

Berlin, Germany
Frag deinen Kühlschrank: Doku über künstliche Intelligenz
ARD-alpha

Frag deinen Kühlschrank: Doku über künstliche Intelligenz

The process: Transforming spaCy’s docs
Increment Magazine

The process: Transforming spaCy’s docs

code
Building Prodigy: Our new tool for efficient machine teaching

Building Prodigy: Our new tool for efficient machine teaching

Prodigy is a project very dear to my heart and seeing it come to life has been one of the most exciting experiences as a software developer so far.
tech 3 minute read
The wired brain: How not to talk about an AI-powered future

The wired brain: How not to talk about an AI-powered future

The way we talk about AI is a mess. It starts with the most obvious, the imagery.
opinion 6 minute read
Announcing Explosion AI

Announcing Explosion AI

Today, we launched the website for our new company, Explosion AI. Explosion is a digital studio specialising in Artificial Intelligence and Natural Language Processing.
personal 6 minute read

I fell for self-help so you don’t have to

I hate to admit it, but during my late teenage years and the beginning of my adult life, I massively fell for self-help blogs.
opinion 6 minute read
The ultimate guide to optimizing annotation workflows

The ultimate guide to optimizing annotation workflows

Tips and advice for how to build efficient human-in-the-loop data development workflows, break down business problems and make the most of automation and model assistance.
tech
Making beautiful slides for your talks, part 7: Resources and tools list

Making beautiful slides for your talks, part 7: Resources and tools list

My ultimate collection of everything you need for your slides, from design assets to presentation tools.
design 5 minute read
Conquering PDFs: document understanding beyond plain text
PyData London

Conquering PDFs: document understanding beyond plain text

In this talk, I present a new and modular approach for building robust document understanding systems, using state-of-the-art models and the awesome Python ecosystem.
London, UK
Applied NLP in the Age of Generative AI: Future-Proof Strategies for Banking and Finance
ECONDAT keynote

Applied NLP in the Age of Generative AI: Future-Proof Strategies for Banking and Finance

A modern approach and mindset for building future-proof NLP pipelines in-house, focusing on use cases from banking, finance and economics.
London, UK
Feminist AI LAN Party
PyCon DE & PyData

Feminist AI LAN Party

Three days of workshops, hacking, creating, publishing and connecting locally, featuring a data development workshop with Prodigy and a session on hacking LLMs.
Darmstadt, Germany
Making beautiful slides for your talks, part 4: Design elements and inspiration

Making beautiful slides for your talks, part 4: Design elements and inspiration

Part 4 of this series dives deeper into the little details and examples of visual design elements you can use to implement your talk’s aesthetic.
design 6 minute read
Feminist AI LAN Party

Feminist AI LAN Party

New project started by Katharine Jarmul and me: a safe, inclusive and hacker-oriented space for experimenting with the intersection of feminism and AI. Join us at PyCon DE & PyData this month!
project
Making beautiful slides for your talks, part 3: Technical content

Making beautiful slides for your talks, part 3: Technical content

In part 3 of this series, I share some tips and inspiration for presenting technical content in your slides and making “boring” topics more fun and engaging.
design 6 minute read
Cracking the Code: How to Start a Career in AI
Welcome to the Jungle

Cracking the Code: How to Start a Career in AI

Short video interview about the 4 skills job hunters can cultivate for a career in artificial intelligence.
From PDFs to AI-ready structured data: a deep dive

From PDFs to AI-ready structured data: a deep dive

A new modular workflow for converting PDFs and similar documents to structured data and how to build end-to-end document understanding pipelines.
tech
Applied NLP with LLMs: Beyond Black-Box Monoliths
PyBerlin

Applied NLP with LLMs: Beyond Black-Box Monoliths

Berlin, Germany
Applied NLP in the Age of Generative AI
PyData Amsterdam keynote

Applied NLP in the Age of Generative AI

In this talk, I’ll share the most important lessons we’ve learned from solving real-world information extraction problems in industry, and show you a new approach and mindset for designing robust and modular NLP pipelines in the age of Generative AI.
Amsterdam, Netherlands
EuroSciPy on Polish TV
TVP3 Szczecin

EuroSciPy on Polish TV

Szczecin, Poland
The Window-Knocking Machine Test

The Window-Knocking Machine Test

How will technology shape our world going forward? And what tools and products should we build? When imagining what the future could look like, it helps to look back in time and compare past visions to our reality today.
opinion 4 minute read
Building the Future of NLP: Insights on spaCy, Prodigy and Generative AI
Leading With Data podcast

Building the Future of NLP: Insights on spaCy, Prodigy and Generative AI

interview
Making beautiful slides for your talks, part 2: All about aesthetics

Making beautiful slides for your talks, part 2: All about aesthetics

After I published my guide to making beautiful slides, I got a lot of great feedback and I especially loved that others had already used it for their talks. In this post, I want to showcase two examples from the community, as well as my most recent talk, and dive deeper into the aesthetics and slide design process.
design 8 minute read
spaCy meets LLMs: Using Generative AI for Structured Data
Data+ML Community Meetup

spaCy meets LLMs: Using Generative AI for Structured Data

Budapest, Hungary
KI – Die künstlerische Intelligenz?
Immergut Festival

KI – Die künstlerische Intelligenz?

We’re discussing the latest developments in Generative AI, hype vs. reality and what those new technologies mean for people, businesses, art, creativity and the music industry.
Neustrelitz, Germany
Post-meetup chat with Hugo Bowne-Anderson
Outerbounds TV

Post-meetup chat with Hugo Bowne-Anderson

interview Berlin, Germany
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
QCon London

The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs

London, UK
My Guide to Berlin

My Guide to Berlin

My personal favourites, tips and recommendations for where to go and what to do in my home city.
personal 7 minute read
Half hour of labeling power: Can we beat GPT?
PyData NYC Workshop

Half hour of labeling power: Can we beat GPT?

New York, US
Panel: Large Language Models
Big PyData BBQ

Panel: Large Language Models

with Alejandro Saucedo (Zalando, Institute for Ethical AI & ML), Alina Lehnhard (Cerence), Michael Gerz (Heidelberg University), Alexander CS Hendorf (Königsweg)
Heidelberg, Germany
Large Language Models: From Prototype to Production
PyData London keynote

Large Language Models: From Prototype to Production

London, UK
The Interhacktives Podcast

Modular Journalism: The new way to find stories?

interview
How the Guardian uses AI to analyse articles
JournalismAI Festival

How the Guardian uses AI to analyse articles

interview
Advanced NLP for Diverse Languages
New Languages for NLP keynote

Advanced NLP for Diverse Languages

Princeton, US
Anecdotes from 11 Role Models in Machine Learning
Towards Data Science

Anecdotes from 11 Role Models in Machine Learning

Interview: Ines Montani & Sebastián Ramírez
PyFest

Interview: Ines Montani & Sebastián Ramírez

interview
spaCy v3: Design concepts explained

spaCy v3: Design concepts explained

code
Episode #300: Building a data science startup
TalkPython podcast

Episode #300: Building a data science startup

Building industrial strength NLP pipelines
Gradient Dissent podcast

Building industrial strength NLP pipelines

interview
Python Bytes podcast

Episode #191: Live from the Manning Python Conference

Chai Time Data Science Interview

Chai Time Data Science Interview

interview
Training an NER model with Prodigy and Transfer Learning

Training an NER model with Prodigy and Transfer Learning

code
SourceSort

Complementing a 15k star open source NLP library with commercial developer tools

interview
kulturnews
“Ines Montani bringt Computern die menschliche Sprache bei. Aber warum wird künstliche Intelligenz trotzdem nicht intelligent?”
interview
“Wir setzen zu viele Hoffnungen in künstliche Intelligenz”
Bayern 2

“Wir setzen zu viele Hoffnungen in künstliche Intelligenz”

interview
spaCy IRL 2019: 2 days of NLP in Berlin

spaCy IRL 2019: 2 days of NLP in Berlin

We were pleased to invite the spaCy community and other folks working on Natural Language Processing to Berlin this summer for a small and intimate event.
Berlin, Germany
FAQ #1: Tips & tricks for NLP, annotation and training

FAQ #1: Tips & tricks for NLP, annotation and training

Custom pipelines and extensions for spaCy v2.0

As spaCy v2.0 gets closer, we've been excited to implement the last outstanding features. One of the best improvements is a new system for adding pipeline components and registering extensions to the Doc, Span and Token objects.
code
Training an insults classifier with Prodigy

Training an insults classifier with Prodigy

code
Story time: How I started coding

Story time: How I started coding

I've seen a couple of these posts pop up over the past year or so, and I've always enjoyed reading other people's stories. So here's mine.
personal 6 minute read

How Front-End Development Can Improve Artificial Intelligence

While researchers rightly focus on better algorithms, there are a lot more things to be done. In this post I'll discuss three ways in which front-end development can improve AI technology.
code
My Year in Review 2025

My Year in Review 2025

On my birthday, I want to take the time again to look back at the past year, including travel, talks, writing and various things I did and enjoyed.
personal 4 minute read
Making beautiful slides for your talks, part 6: Community showcase

Making beautiful slides for your talks, part 6: Community showcase

Part 6 of my slides series showcases more examples from the community for inspiration, with details on the design, aesthetic and creation process.
design 8 minute read
Sovereign AI systems instead of black box solutions
it-daily

Sovereign AI systems instead of black box solutions

German article featuring my take on AI in industry, the role of open source, and using Generative AI to create systems.
Episode #504: Developer Trends in 2025
TalkPython podcast

Episode #504: Developer Trends in 2025

interview
Conquering PDFs: document understanding beyond plain text
PyCon DE & PyData

Conquering PDFs: document understanding beyond plain text

In this talk, I’ll present a new and modular approach for building robust document understanding systems, using state-of-the-art models and the awesome Python ecosystem.
Darmstadt, Germany
UNMUTE IT podcast

KI ohne Ketten: Warum Open Source gegen Big Tech gewinnen kann

interview
How to advocate for modular NLP in the age of Generative AI

How to advocate for modular NLP in the age of Generative AI

With all the hype around Generative AI, how can you, as a developer, communicate the nuances and advocate for new and modular solutions that are better, easier and cheaper?
opinion
What the history of the web can teach us about the future of AI

What the history of the web can teach us about the future of AI

How will AI development look in the future? I think there is a lot we can learn from another groundbreaking technology: the web.
opinion
My Year in Review 2024

My Year in Review 2024

2024 was an eventful but also difficult year for me. This is my personal summary, including travel, talks, writing and various things I did and enjoyed.
personal 5 minute read
Accelerate your Career with Open-Source AI
dotAI

Accelerate your Career with Open-Source AI

Panel discussion about making a career out of open-source software, featuring Gael Varoquaux (scikit-learn), Steeve Morin (ZML) and me.
Paris, France
The 100 who are shaping AI in Europe
l’Opinion

The 100 who are shaping AI in Europe

Honoured to be part of this list by French newspaper l’Opinion, alongside many other cool people.
How GitLab uses spaCy to analyze support tickets and empower their community

How GitLab uses spaCy to analyze support tickets and empower their community

A case study on GitLab’s large-scale NLP pipelines for extracting actionable insights from support tickets and usage questions.
tech
10 Years of Open Source: Navigating the Next AI Revolution
EuroSciPy keynote

10 Years of Open Source: Navigating the Next AI Revolution

In this talk, I’ll share the most important lessons we’ve learned in 10 years of working on open-source software, our core philosophies that helped us adapt to an ever-changing AI landscape and why open source and interoperability still wins over black-box, proprietary APIs.
Szczecin, Poland
Back to our roots: Company update and future plans

Back to our roots: Company update and future plans

We’re back to running Explosion as a smaller, independent-minded and self-sufficient company. spaCy and Prodigy will continue, and we'll keep updating our stack with the latest technologies, without changing its core identity or purpose.
news
The AI Revolution Will Not Be Monopolized
InfoQ

The AI Revolution Will Not Be Monopolized

Daniel Dominguez summarises the key takeaways from my recent talk at QCon.
London, UK
How S&P Global is making markets more transparent with NLP, spaCy and Prodigy

How S&P Global is making markets more transparent with NLP, spaCy and Prodigy

A case study on S&P Global’s efficient information extraction pipelines for real-time commodities trading insights in a high-security environment.
tech
Three transformative tools: a review of my favourite apps

Three transformative tools: a review of my favourite apps

There’s this feeling of joy and excitement you sometimes get when you start using a new tool, discover the little details that make a product great and feel the rush of motivation and new ideas that comes with it. It’s what I’ve always aspired to do with our products, too, and it’s what motivated this blog post.
tech 7 minute read
Ines Montani at QCon London: Economies of Scale Can’t Monopolise the AI Revolution
InfoQ Magazine

Ines Montani at QCon London: Economies of Scale Can’t Monopolise the AI Revolution

London, UK
The AI Revolution Will Not Be Monopolized: Behind the scenes
Open Source ML Mixer

The AI Revolution Will Not Be Monopolized: Behind the scenes

A more in-depth look at the concepts and ideas, academic literature, related experiments and preliminary results for distilled task-specific models.
Berlin, Germany
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
PyCon Lithuania keynote

The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs

With the latest advancements in NLP and LLMs, and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big tech monopolies? I don’t think so, and in this talk, I’ll show you why.
Vilnius, Lithuania
New Explosion website

New Explosion website

We’ve revamped our website to focus more on all the great content by the team and across our stack and ecosystem.
news
Explosion, NLP, Generative AI, Entrepreneurship
Learning From Machine Learning

Explosion, NLP, Generative AI, Entrepreneurship

interview
Teaching Python Podcast

NLP with Ines Montani

interview
Raspberry Pi, Python and cats: my first foray into embedded development

Raspberry Pi, Python and cats: my first foray into embedded development

I love shitty robots. And I love Python, and cats.
tech 4 minute read
NLP: From Prototype to Production
Outerbounds Fireside Chat

NLP: From Prototype to Production

interview
Console DevTools Podcast

Data Science with Ines Montani

interview
Introducing spaCy Tailored Pipelines

Introducing spaCy Tailored Pipelines

Explosion is pleased to announce a new development services offering, spaCy Tailored Pipelines. We’ll build you a custom natural language processing pipeline, delivered in a standardized format using spaCy’s projects system.
news
We’ve sold 5% of Explosion

We’ve sold 5% of Explosion

Since founding Explosion we've run the company as a profitable business. We now want to release more things and expand the team, without compromising our direction or stability. We’re pleased to announce that we’ve found an investment that ticks all the boxes.
news
Building Industrial-Strength NLP Applications
Snorkel ScienceTalks

Building Industrial-Strength NLP Applications

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

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

code
TalkPython podcast

Episode #297: Python year in review 2020

spaCy v3.0: Bringing State-of-the-art NLP from Prototype to Production

spaCy v3.0: Bringing State-of-the-art NLP from Prototype to Production

Global AI Live (digital)
Designing Practical NLP Solutions

Designing Practical NLP Solutions

L3-AI (digital)
Image captioning with Prodigy and PyTorch

Image captioning with Prodigy and PyTorch

code
The Future of NLP in Python
PyCon Colombia keynote

The Future of NLP in Python

Medellìn, Colombia
Backstage Talk: Zündfunk Netzkongress
Bayerischer Rundfunk

Backstage Talk: Zündfunk Netzkongress

interview

Interview by Sayak Paul

In this interview, I talk about how I got into programming, how we stay up to date with the latest developments in our field and the ideas behind my PyCon India keynote “Let Them Write Code”.
interview
spaCy meets Transformers

spaCy meets Transformers

Huge transformer models like BERT, GPT-2 and XLNet have set a new standard for accuracy on almost every NLP leaderboard. You can now use these models in spaCy via a new interface library.
code
Advanced NLP with spaCy

Advanced NLP with spaCy

In this free interactive online course you’ll learn how to use spaCy to build advanced natural language understanding systems, using both rule-based and machine learning approaches.
code
TalkPython podcast

Building a software business

In this episode, Michael Kennedy and I talk about building a sustainable software business on open source and Python.
interview
How to Ignore Most Startup Advice and Build a Decent Software Business
EuroPython keynote

How to Ignore Most Startup Advice and Build a Decent Software Business

Edinburgh, UK

Reflections on running spaCy: commercial open-source NLP

As more and more people and companies are getting involved with open-source software, balancing the expectations of an open community and a traditional provider vs. consumer relationship is becoming increasingly difficult.
opinion 9 minute read

Supervised learning is great — it’s data collection that’s broken

The dissatisfaction with supervised learning is misplaced. Instead of waiting for the unsupervised messiah to arrive, we need to fix the way we're collecting and reusing human knowledge.
code

5 things I learned from working in print

For four years, I worked for a popular print magazine.
opinion 4 minute read

Selected Talks

2026-07-24
Coming soon
keynote
PyData PyCon Yerevan · Yerevan, Armenia
2026-06-07
Vibe NLP for Applied NLP
PyData London · London, UK
2026-04-16
Panel: Open Source as a Business — Models, Paths, and Practice
discussion
PyCon DE & PyData · Darmstadt, Germany
2026-04-16
Vibe NLP for Applied NLP
PyCon DE & PyData · Darmstadt, Germany
2026-04-16
Panel: Evolution, Revolution, or Illusion? The Future of Python and Coding in the Age of AI
discussion
PyCon DE & PyData · Darmstadt, Germany
2025-12-10
PDFs bezwingen: Dokumentenanalyse über reinen Text hinaus (German)
Bitkom AK Legal Tech · Berlin, Germany
2025-12-02
Guest lecture: Industrial-Strength Natural Language Processing with spaCy and Prodigy
Humboldt University · Berlin, Germany
2025-11-16
Panel: AI and its Impact
discussion
PyCon Ireland · Dublin, Ireland
2025-11-15
Building AI with AI
keynote
PyCon Ireland · Dublin, Ireland
2025-06-16
Conquering PDFs: document understanding beyond plain text
Build with AI · Berlin, Germany
2025-06-07
Conquering PDFs: document understanding beyond plain text
PyData London · London, United Kingdom
2025-06-05
Applied NLP in the Age of Generative AI: Future-Proof Strategies for Banking and Finance
keynote
ECONDAT · London, United Kingdom
2025-05-14
Conquering PDFs: document understanding beyond plain text
PyBerlin · Berlin, Germany
2025-04-24
AI in Reality Fireside Chat: Enterprise AI & Open-Source Innovation
discussion
PyCon DE & PyData · Darmstadt, Germany
2025-04-23
Conquering PDFs: document understanding beyond plain text
PyCon DE & PyData · Darmstadt, Germany
2025-04-17
Applied NLP in the Age of Generative AI
Google Developer Groups · Berlin, Germany
2025-04-10
KI zwischen Freiheit und Kontrolle: The AI Revolution Will Not Be Monopolized (German)
data:unplugged · Münster, Germany
2025-03-07
Künstliche Intelligenz: Technologie der Zukunft – und warum Open Source die Karten neu mischt (German)
Heise KI-Woche 2025
2025-01-25
What the history of the web can teach us about the future of AI
keynote
PyCon+Web · Berlin, Germany
2024-12-07
PyLadies entrepreneurs and career development
discussion
PyLadiesCon
2024-11-03
Reality is not an End-to-End Prediction Problem: Applied NLP in the Age of Generative AI
keynote
PyCon FR · Strasbourg, France
2024-10-17
Accelerate your Career with Open-Source AI
discussion
dotAI · Paris, France
2024-10-17
Reality is not an End-to-End Prediction Problem: Applied NLP in the Age of Generative AI
dotAI · Paris, France
2024-10-09
Applied NLP with LLMs: Beyond Black-Box Monoliths
PyBerlin · Berlin, Germany
2024-10-02
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
O’Reilly Software Development Superstream
2024-09-26
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
InfoQ Dev Summit · Munich, Germany
2024-09-20
Applied NLP in the Age of Generative AI
keynote
PyData Amsterdam · Amsterdam, Netherlands
2024-08-29
Beautiful Slides for Beginners
lightning talk
EuroSciPy · Szczecin, Poland
2024-08-28
10 Years of Open Source: Navigating the Next AI Revolution
keynote
EuroSciPy · Szczecin, Poland
2024-08-09
Applied NLP in the Age of Generative AI
keynote
DataHack Summit · Bengaluru, India
2024-06-15
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
PyData London · London, United Kingdom
2024-06-12
Towards Structured Data: LLMs from Prototype to Production
U.S. Census Bureau: Center for Optimization and Data Science Seminar
2024-06-11
spaCy meets LLMs: Using Generative AI for Structured Data
Data+ML Community Meetup · Budapest, Hungary
2024-06-11
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
Budapest ML Forum · Budapest, Hungary
2024-06-01
KI – Die künstlerische Intelligenz? (German)
discussion
Immergut Festival · Neustrelitz, Germany
2024-05-24
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
PyCon Italia · Florence, Italy
2024-04-24
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
PyCon DE & PyData Berlin · Berlin, Germany
2024-04-21
The AI Revolution Will Not Be Monopolized: Behind the scenes
Open Source ML Mixer · Berlin, Germany
2024-04-09
Connecting the Dots: Applying Generative AI
discussion
QCon · London, United Kingdom
2024-04-08
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
QCon · London, United Kingdom
2024-04-05
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
keynote
PyCon Lithuania · Vilnius, Lithuania
2023-11-29
Incorporating LLMs into practical NLP workflows
PyBerlin · Berlin, Germany
2023-11-01
Half hour of labeling power: Can we beat GPT?
tutorial
PyData NYC · New York, United States
2023-09-21
Panel: Large Language Models
discussion
Big PyData BBQ · Heidelberg, Germany
2023-09-21
Large Language Models: From Prototype to Production
Big PyData BBQ · Heidelberg, Germany
2023-09-16
There are no bad labels, only happy accidents
tutorial
PyData Amsterdam · Amsterdam, Netherlands
2023-07-19
Large Language Models: From Prototype to Production
keynote
EuroPython · Prague, Czech Republic
2023-06-03
Large Language Models: From Prototype to Production
keynote
PyData London · London, United Kingdom
2023-05-24
Welchen Einfluss hat generative KI auf die politische Meinungsbildung? (German)
discussion
FZI Spot On: ChatGPT & Co. · Berlin, Germany
2023-04-17
Incorporating LLMs into practical NLP workflows
PyCon DE & PyData Berlin · Berlin, Germany
2022-12-08
How the Guardian uses AI to analyse articles
discussion
JournalismAI Festival
2022-05-12
Solutions for Advanced NLP for Diverse Languages
keynote
New Languages for NLP · Princeton, United States
2021-06-17
Applied NLP Thinking
L3-AI
2021-06-10
What does “real-world NLP” look like and how can students get ready for it?
keynote
Teaching NLP (NAACL 2021)
2020-10-22
spaCy v3.0: Bringing State-of-the-art NLP from Prototype to Production
keynote
Global AI Live
2020-06-18
Designing Practical NLP Solutions
L3-AI
2020-02-08
The Future of NLP in Python
keynote
PyCon Colombia · Medellín, Colombia
2019-11-09
Künstliche Intelligenz beyond the hype (German)
Zündfunk Netzkongress · Munich, Germany
2019-10-13
Let Them Write Code
keynote
PyCon India · Chennai, India
2019-10-09
spaCy and the future of multi-lingual NLP
META Forum Award Ceremony · Brussels, Belgium
2019-07-06
spaCy and Explosion: past, present and future
spaCy IRL · Berlin, Germany
2019-05-09
Practical NLP transfer learning with spaCy and Prodigy
InfoShare · Gdańsk, Poland
2019-01-28
Practical transfer learning for NLP with spaCy and Prodigy
Applied Machine Learning Days · Lausanne, Switzerland
2018-11-22
The AI Revolution will not be Monopolized
Hack Talks · Helsinki, Finland
2018-07-26
How to Ignore Most Startup Advice and Build a Decent Software Business
keynote
EuroPython · Edinburgh, Scotland
2018-05-05
Teaching AI about Human Knowledge
PyDays · Vienna, Austria
2018-04-14
Increasing Data Science Productivity: spaCy & Prodigy
San Francisco, United States
2018-04-12
Rapid NLP Annotation Through Binary Decisions, Pattern Bootstrapping and Active Learning
TomTom Founders Festival · Charlottesville, United States