University of Cambridge > Talks.cam > NLIP Seminar Series > Learning to Generate Natural Source Code

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Learning to Generate Natural Source Code

Download to your calendar using vCal

If you have a question about this talk, please contact Tamara Polajnar .

Natural source code is source code that is written by and meant to be understood by humans. I’ll talk about recent efforts to build generative models that (a) capture the structure present in source code, and (b) can be learned efficiently from large repositories of existing code. Our approach builds upon the fast training of neural probabilistic language models work of Mnih & Teh (2012), but incorporates hierarchical structure and much additional source code-specific structure. Empirically, our new models substantially outperform existing language models in terms of log probability of held out data, and samples from the learned models look more like real source code.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Pippard Lecture Theatre, Cavendish Laboratory, J.J. Thomson Avenue Large Seminar Room, 1st floor, Institute of Public Health, Forvie Site, Cambridge BioMedical Campus, CB2 0SR Average on weekdays: 9195.37373096 kWh

Other talks

Title to be confirmed Title TBC Precarity and the economy of makeshifts: A novel argument from the census of England, 1851-1911 TBC Title to be confirmed Studying viruses to understand what makes pandemic viruses special and how innate immunity works
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity