Open Vocabulary Learning on Source Code with a Graph-Structured Cache
Milan Cvitkovic, Badal Singh, Animashree Anandkumar
Abstract
Machine learning models that take computer program source code as input typically use Natural Language Processing (NLP) techniques. However, a major challenge is that code is written using an open, rapidly changing vocabulary due to, e.g., the coinage of new variable and method names. Reasoning over such a vocabulary is not something for which most NLP methods are designed. We introduce a Graph-Structured Cache to address this problem; this cache contains a node for each new word the model encounters with edges connecting each word to its occurrences in the code. We find that combining this graph-structured cache strategy with recent Graph-Neural-Network-based models for supervised learning on code improves the models’ performance on a code completion task and a variable naming task — with over 100% relative improvement on the latter — at the cost of a moderate increase in computation time.
BibTeX
@InProceedings{pmlr-v97-cvitkovic19b,
title = {Open Vocabulary Learning on Source Code with a Graph-Structured Cache},
author = {Cvitkovic, Milan and Singh, Badal and Anandkumar, Animashree},
booktitle = {Proceedings of the 36th International Conference on Machine Learning},
pages = {1475--1485},
year = {2019},
editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
volume = {97},
series = {Proceedings of Machine Learning Research},
month = {09--15 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v97/cvitkovic19b/cvitkovic19b.pdf},
url = {https://proceedings.mlr.press/v97/cvitkovic19b.html},
abstract = {Machine learning models that take computer program source code as input typically use Natural Language Processing (NLP) techniques. However, a major challenge is that code is written using an open, rapidly changing vocabulary due to, e.g., the coinage of new variable and method names. Reasoning over such a vocabulary is not something for which most NLP methods are designed. We introduce a Graph-Structured Cache to address this problem; this cache contains a node for each new word the model encounters with edges connecting each word to its occurrences in the code. We find that combining this graph-structured cache strategy with recent Graph-Neural-Network-based models for supervised learning on code improves the models’ performance on a code completion task and a variable naming task — with over 100% relative improvement on the latter — at the cost of a moderate increase in computation time.}
}