Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code

Rafael-Michael Karampatsis, Hlib Babii, Romain Robbes, Charles Sutton, Andrea Janes

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Statistical language modeling techniques have successfully been applied to large source code corpora, yielding a variety of new software development tools, such as tools for code suggestion, improving readability, and API migration. A major issue with these techniques is that code introduces new vocabulary at a far higher rate than natural language, as new identifier names proliferate. Both large vocabularies and out-of-vocabulary issues severely affect Neural Language Models (NLMs) of source code, degrading their performance and rendering them unable to scale. In this paper, we address this issue by: 1) studying how various modelling choices impact the resulting vocabulary on a large-scale corpus of 13,362 projects; 2) presenting an open vocabulary source code NLM that can scale to such a corpus, 100 times larger than in previous work; and 3) showing that such models outperform the state of the art on three distinct code corpora (Java, C, Python). To our knowledge, these are the largest NLMs for code that have been reported. All datasets, code, and trained models used in this work are publicly available.
Original languageEnglish
Title of host publicationICSE '20: Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering
PublisherAssociation for Computing Machinery (ACM)
Pages1073-1085
Number of pages13
ISBN (Print)9781450371216
DOIs
Publication statusPublished - 27 Jun 2020
Event42nd International Conference on Software Engineering - Online
Duration: 24 Jun 202016 Jul 2020
https://2020.icse-conferences.org/

Conference

Conference42nd International Conference on Software Engineering
Abbreviated titleICSE 2020
CityOnline
Period24/06/2016/07/20
Internet address

Keywords / Materials (for Non-textual outputs)

  • Naturalness of code
  • Neural Language Models
  • Byte-Pair Encoding

Fingerprint

Dive into the research topics of 'Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code'. Together they form a unique fingerprint.

Cite this