`

Timezone: »

 
Poster
Program Synthesis and Semantic Parsing with Learned Code Idioms
Richard Shin · Miltiadis Allamanis · Marc Brockschmidt · Oleksandr Polozov

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #168
in Applications -- Program Understanding and Generation »

Program synthesis of general-purpose source code from natural language specifications is challenging due to the need to reason about high-level patterns in the target program and low-level implementation details at the same time. In this work, we present Patois, a system that allows a neural program synthesizer to explicitly interleave high-level and low-level reasoning at every generation step. It accomplishes this by automatically mining common code idioms from a given corpus, incorporating them into the underlying language for neural synthesis, and training a tree-based neural synthesizer to use these idioms during code generation. We evaluate Patois on two complex semantic parsing datasets and show that using learned code idioms improves the synthesizer's accuracy.

Keywords: Applications · Program Understanding and Generation · Algorithms -> Structured Prediction; Applications -> Natural Language Processing; Deep Learning · Generative Models; Probabili
[ Paper]  [ Slides] 

Author Information

Richard Shin (UC Berkeley)
Miltiadis Allamanis (Microsoft Research)
Marc Brockschmidt (Microsoft Research)
Oleksandr Polozov (Microsoft Research)

More from the Same Authors