Timezone: »

 
Poster
SPoC: Search-based Pseudocode to Code
Sumith Kulal · Panupong Pasupat · Kartik Chandra · Mina Lee · Oded Padon · Alex Aiken · Percy Liang

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #169
in Applications -- Program Understanding and Generation »

We consider the task of mapping pseudocode to executable code, assuming a one-to-one correspondence between lines of pseudocode and lines of code. Given test cases as a mechanism to validate programs, we search over the space of possible translations of the pseudocode to find a program that compiles and passes the test cases. While performing a best-first search, compilation errors constitute 88.7% of program failures. To better guide this search, we learn to predict the line of the program responsible for the failure and focus search over alternative translations of the pseudocode for that line. For evaluation, we collected the SPoC dataset (Search-based Pseudocode to Code) containing 18,356 C++ programs with human-authored pseudocode and test cases. Under a budget of 100 program compilations, performing search improves the synthesis success rate over using the top-one translation of the pseudocode from 25.6% to 44.7%.

Keywords: Natural Language Processing · Applications · Program Understanding and Generation
[ Paper]  [ Poster] 

Author Information

Sumith Kulal (Stanford University)
Panupong Pasupat (Stanford University)
Kartik Chandra (Stanford University)
Mina Lee (Stanford University)
Oded Padon (Stanford University)
Alex Aiken (Stanford University)
Percy Liang (Stanford University)

More from the Same Authors