SPLASH 2022
Mon 5 - Sat 10 December 2022 Auckland, New Zealand
Fri 9 Dec 2022 14:00 - 14:30 at Seminar Room G007 - Debugging Chair(s): Neville Grech

We present Seq2Parse, a language-agnostic neurosymbolic approach to automatically repairing parse errors. Seq2Parse is based on the insight that Symbolic Error Correcting (EC) Parsers can, in principle, synthesize repairs, but, in practice, are overwhelmed by the many error-correction rules that are not relevant to the particular program that requires repair. In contrast, Neural approaches are fooled by the large space of possible sequence level edits, but can precisely pinpoint the set of EC-rules that are relevant to a particular program. We show how to combine their complementary strengths by using neural methods to train a sequence classifier that predicts the small set of relevant EC-rules for an ill-parsed program, after which, the symbolic EC-parsing algorithm can make short work of generating useful repairs. We train and evaluate our method on a dataset of 1,100,000 Python programs, and show that Seq2Parse is accurate and efficient: it can parse 94% of our tests within 2.1 seconds, while generating the exact user fix in 1 out 3 of the cases; and useful: humans perceive both Seq2Parse-generated error locations and repairs to be almost as good as human-generated ones in a statistically-significant manner.

Fri 9 Dec

Displayed time zone: Auckland, Wellington change

13:30 - 14:30
DebuggingOOPSLA at Seminar Room G007
Chair(s): Neville Grech University of Malta
13:30
30m
Talk
AnICA: Analyzing Inconsistencies in Microarchitectural Code Analyzers
OOPSLA
Fabian Ritter Saarland University, Germany, Sebastian Hack Saarland University, Germany
DOI
14:00
30m
Talk
Seq2Parse: Neurosymbolic Parse Error Repair
OOPSLA
Georgios Sakkas University of California at San Diego, Madeline Endres University of Michigan, Philip J. Guo University of California at San Diego, Westley Weimer University of Michigan, Ranjit Jhala University of California at San Diego
DOI
Hide past events