Thread by @sourcedtech

@francesc @vadimlearning First #MLonCode paper presented by @vadimlearning is "code2vec: Learning Distributed Representations of Code" by Uri Alon, Meital Zilberstein, @omerlevy_, and @yahave.

arxiv.org/abs/1803.09473

@francesc @vadimlearning @omerlevy_ @yahave The second #MLonCode paper, also presented by @vadimlearning, is "A General Path-Based Representation for Predicting Program Properties" by ... wait for it ... Uri Alon, Meital Zilberstein, @omerlevy_, and @yahave 🎉

arxiv.org/abs/1803.09544

@francesc @vadimlearning @omerlevy_ @yahave Next, our #ML intern Romain Keramitas, is reviewing the #MLonCode paper "Mining Idioms from Source Code" by Miltiadis Allamanis and @RandomlyWalking

arxiv.org/abs/1404.0417

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking Up next, @kslavnov presents the #MLonCode paper "De-anonymizing Programmers via Code Stylometry" by Aylin Caliskan-Islam, Richard Harang, Andrew Liu, Arvind Narayanan, Clare Voss, Fabian Yamaguchi, and Rachel Greenstadt

usenix.org/node/190845 (this ones comes with a video!)

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov And now, the #MLonCode with probably the longest title ever "The Impact of IR-based Classifier Configuration on the Performance and the Effort of Method-Level Bug Localization"

arxiv.org/abs/1806.07727

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov And now @egor_bu reviews "Learning Natural Coding Conventions" by Miltiadis Allamanis, Earl T. Barr, @christianbird, and @RandomlyWalking

This is probably one my favorite #MLonCode papers, such a promising idea!

arxiv.org/abs/1402.4182

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov @egor_bu @christianbird And @egor_bu now continues the #MLonCode review meeting by talking about "Estimating defectiveness of source code: A predictive model using GitHub content" by Ritu Kapur and Balwinder Sodhi

arxiv.org/abs/1803.07764

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov @egor_bu @christianbird Now switching to bug prediction themed #MLonCode papers, @egor_bu is now reviewing "Entropy Guided Spectrum Based Bug Localization Using Statistical Language Model" by Saikat Chakraborty, Yujian Li, Matt Irvine, Ripon Saha, Baishakhi Ray

arxiv.org/abs/1802.06947

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov @egor_bu @christianbird And now Gabor Markowski, another one of our interns, presents remotely "Semantic Code Repair using Neuro-Symbolic Transformation Networks" by Jacob Devlin, Jonathan Uesato, Rishabh Singh, Pushmeet Kohli

arxiv.org/abs/1710.11054

#MLonCode #MachineLearning

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov @egor_bu @christianbird Next #MLonCode paper is "Automated software vulnerability detection with machine learning" by Jacob A. Harer et al.

The presenter is again our intern @Fulaphex presenting all the way from Poland 🇵🇱

arxiv.org/abs/1803.04497

#MachineLearning #MLonCode

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov @egor_bu @christianbird @Fulaphex And the third paper presented by @Fulaphex: "Syntax and Sensibility: Using language models to detect and correct syntax errors" by @_eddieantonio et al

ieeexplore.ieee.org/document/83302…

#MLonCode #MachineLearning

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov @egor_bu @christianbird @Fulaphex @_eddieantonio And we're down to three papers!

Up next @Fulaphex presents "Detecting API Documentation Errors" by @_zhong_hao and @zhendongsu from the Institute of Software at the Chinese Academy of Sciences

dl.acm.org/citation.cfm?i…

#MLonCode #MachineLearning

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov @egor_bu @christianbird @Fulaphex @_eddieantonio @_Zhong_Hao @zhendongsu and to finish the #MLonCode review, our intern Romain Keramitas is back to the stage to present two papers:

"Deep Learning to Detect Redundant Method Comments" by Annie Louis et al from @edinburghnlp

arxiv.org/abs/1806.04616

#MLonCode #MachineLearning

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov @egor_bu @christianbird @Fulaphex @_eddieantonio @_Zhong_Hao @zhendongsu @EdinburghNLP and last but definitely not least, Romain presents "Deep Reinforcement Learning for Programming Language Correction" by Rahul Gupta, Aditya Kanade, Shirish Shevade

arxiv.org/abs/1801.10467

#MLonCode #MachineLearning

@francesc @vadimlearning @omerlevy_ @yahave @RandomlyWalking @kslavnov @egor_bu @christianbird @Fulaphex @_eddieantonio @_Zhong_Hao @zhendongsu @EdinburghNLP And with this we're done with #MLonCode review papers!
Up next a chat with the #ML team and all attendees.

Thanks everyone for joining, and thanks for the authors of all the papers ❤️

The video will be released soon.
Join the slack at sourced.tech to be notified.