Neural language models for network configuration: Opportunities and reality check

TL;DR

This paper reviews recent deep learning advances in NLP and programming languages, evaluating their potential and limitations for automating network configuration tasks like verification, synthesis, and translation.

Contribution

It provides a comprehensive survey of deep learning techniques applied to programming languages and assesses their applicability to network configuration automation.

Findings

Deep learning models show promise for network configuration tasks.

Training requirements vary significantly across models.

Performance in networking applications remains uncertain.

Abstract

Boosted by deep learning, natural language processing (NLP) techniques have recently seen spectacular progress, mainly fueled by breakthroughs both in representation learning with word embeddings (e.g. word2vec) as well as novel architectures (e.g. transformers). This success quickly invited researchers to explore the use of NLP techniques to other fields, such as computer programming languages, with the promise to automate tasks in software programming (bug detection, code synthesis, code repair, cross language translation etc.). By extension, NLP has potential for application to network configuration languages as well, for instance considering tasks such as network configuration verification, synthesis, and cross-vendor translation. In this paper, we survey recent advances in deep learning applied to programming languages, for the purpose of code verification, synthesis and translation: in particularly, we review their training requirements and expected performance, and qualitatively assess whether similar techniques can benefit corresponding use-cases in networking.