TY - JOUR
T1 - SPoC
T2 - 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019
AU - Kulal, Sumith
AU - Pasupat, Panupong
AU - Chandra, Kartik
AU - Lee, Mina
AU - Padon, Oded
AU - Aiken, Alex
AU - Liang, Percy
N1 - Publisher Copyright:
© 2019 Neural information processing systems foundation. All rights reserved.
PY - 2019
Y1 - 2019
N2 - 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%.
AB - 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%.
UR - http://www.scopus.com/inward/record.url?scp=85090169685&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???
AN - SCOPUS:85090169685
SN - 1049-5258
VL - 32
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
Y2 - 8 December 2019 through 14 December 2019
ER -