Write a Blog >>
ASE 2021
Sun 14 - Sat 20 November 2021 Australia
Wed 17 Nov 2021 12:20 - 12:40 at Kangaroo - Learning II Chair(s): John Grundy

This paper presents Arvada, an algorithm for learning context-free grammars from a set of positive examples and a Boolean-valued oracle. Arvada learns a context-free grammar by building parse trees from the positive examples. Starting from initially flat trees, Arvada builds structure to these trees with a key operation: it \emph{bubbles} sequences of sibling nodes in the trees into a new node, adding a layer of indirection to the tree. Bubbling operations enable recursive generalization in the learned grammar. We evaluate Arvada against GLADE and find it achieves on average increases of 4.98$\times$ in recall and 3.13$\times$ in F1 score, while incurring only a 1.27$\times$ slowdown and requiring only 0.87$\times$ as many calls to the oracle. Arvada has a particularly marked improvement over GLADE on grammars with highly recursive structure, like those of programming languages.

Wed 17 Nov

Displayed time zone: Hobart change

12:00 - 13:00
Learning IIResearch Papers / Industry Showcase at Kangaroo
Chair(s): John Grundy Monash University
On Multi-Modal Learning of Editing Source Code
Research Papers
Saikat Chakraborty Columbia University, Baishakhi Ray Columbia University
Learning Highly Recursive Input Grammars
Research Papers
Neil Kulkarni University of California, Berkeley, Caroline Lemieux Microsoft Research, Koushik Sen University of California at Berkeley
Link to publication Pre-print
Learning GraphQL Query Cost
Industry Showcase
Georgios Mavroudeas Rensselaer Polytechnic Institute, Guillaume Baudart Inria; ENS; PSL University, Alan Cha IBM Research, USA, Martin Hirzel IBM Research, Jim A. Laredo IBM Research, Malik Magdon-Ismail Rensselaer Polytechnic Institute, Louis Mandel IBM Research, USA, Erik Wittern IBM Research