#MLonCode

Try out a GitHub action prototype stemming from Typilus our PLDI 2020 paper Joint work with @EarlTBarr1 S. Ducousso, Z. Gao #MLonCode Feedback and contributions are always welcome!

Suggested Python Type Annotations via GitHub Actions using Machine Learning (commit suggestions) from @miltos1 📢 A great example of using ML w/Actions and 🚀 cool products for the community. #MachineLearningOnCode #MLonCode

Detecting licenses in code with @golang and #MachineLearning by @vadimlearning #MLonCode

Au revoir @Docker, Hello @sourcedtech #MLonCode

What if a Machine Learning Model could learn how to code? We are doing it! 🏆 We are excited to release #codeBERT. It's a MLM trained over Python source code thx to @huggingface 🕹 To easily load the model and its weights (code below) #MLonCode #NLP #CodeMining #DeepLearning

Announcing source{d} Engine beta for Code Retrieval and Analysis and source{d} Lookout Alpha for Assisted Code Review #CodeAsData #MLonCode

Feel honored to present today at @Google Montreal, on behalf of the @sourcedtech team, our work on developer similiraty in front of such #MLonCode pioneers #ML4SE #EngineeringObservability The poster designed for the occasion 👨‍🎨👇

Today we're at #FOSD, talking about the future of software development with influential individuals in the fields of #MLonCode, #QuantumComputing, and #blockchain technologies. Follow this thread for live tweeting!

"We need to teach computers how to understand loops" and other future directions of the #MLonCode field by Sergio Giro #FOSD

@yahave is now shouting (literally because he doesn't want to use the mic 😅) about #MLonCode and the danger of developing a "clippy" for programmers Hilarious talk and brilliant demo at #FOSD

Check out the video and slides from @vadimlearning's talk at @dotConferences #dotAI about #MLonCode

[Slides] Measuring code sentiment in a #Git repository by @vadimlearning at @GopherConRu #MLonCode

Announcing Public Git Archive ( for static analysis and #MLonCode 3 Terabytes of GitHub repositories (all projects >50 stars) with meta data, stored as rooted repositories, and easily downloadable over HTTP with the pga tool (

We released a new #MLonCode dataset: @docker hub metadata. 1.46mm configurations and manifests which you can use to recover the Dockerfile-s. This is the first milestone of @TristanKalos's internship project at @sourcedtech, and more datasets are coming.

The Case for Data-Driven #OpenSource Development by @eisokant via @thenewstack #CodeAsData #MLonCode

I am excited to share research my colleague Ho-Hsiang and I have done that uses deep learning to build semantic search on code. We provide a fully reproducible example. Amazing demo of #MLonCode @Github. Thanks to @fastdotai for the tools/ideas!

Narrow Meaning Identifiers increase code understandability by 80% - Asher Trockman applied #MLonCode on #msr18

Generating code embeddings: How #MachineLearning can bridge the gap between #NLP and code by @tiferet from @github #MLonCode s

Did you know that the @sourcedtech team curates a list of 🆒links & research papers related to #MachineLearning applied to source code? (#MLonCode) contributions welcome! 🎉

Really interesting paper on #MLonCode with an approach based on paths in ASTs "code2vec: Learning Distributed Representations of Code" by Uri Alon, Meital Zilberstein, @omerlevy_, and @yahave Take this as an open invitation to visit our offices 😊 📖:

Creating a #model to predict areas of PRs that will generate comments on, using a combination of historic comment data and mailing list stack traces by @holdenkarau and @krisnova at @FOSDEM #MLonCode

Don't believe in what I see: #MLonCode devroom on @fosdem 2019! Big shout out to @francesc who did the paperwork. Please submit your talks.

New #OpenSourceShow 12/11: @francesc returns to talk about #MLonCode, share his favorite tips and why it’s made him a better developer, plus how and where you can get started. Catch up on past shows >