What's new

Software Engineering & AI

Learning to Edit Code

From the thesis:
We further define a pre-training objective, “naturalization”, to pre-train the models with natural coding conventions followed by the developers. In this work, we take developers’ written code and apply semantic-preserving code transformation to make the code “unnatural” and “weird”. We ask a model to transform those unnatural codes into their orig- inal forms. With such a training mechanism, we aim to make the model implicitly biased towards the natural coding...


  • Learning to Edit Code - Thesis.pdf
    2.7 MB · Views: 0
Last edited:

AI for Software Engineering

Software making software to make software…

Almost all articles on this subject (see below) suggest that one day software will be able to reliably build complex software…but not anytime soon. In the meantime, AI will be helping software developers and creating basic applications, such as with the help of DSL (domain specific languages), natural language processing, and deep learning.

On the academic side, a research article with over 200 citations is DeepCoder: Learning to...
Last edited:


Source: https://ckaestne.github.io/seai/