HackerPapers

arXiv:1802.08979cs.CL

NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System

Xi Victoria Lin, Chenglong Wang, Luke Zettlemoyer, Michael D. Ernst

Abstract

We present new data and semantic parsing methods for the problem of mapping English sentences to Bash commands (NL2Bash). Our long-term goal is to enable any user to perform operations such as file manipulation, search, and application-specific scripting by simply stating their goals in English. We take a first step in this domain, by providing a new dataset of challenging but commonly used Bash commands and expert-written English descriptions, along with baseline methods to establish performance levels on this task.

arXiv comments
Accepted at the Language Resource and Evaluation Conference (LREC) 2018
Journal reference
DOI
Subjects
cs.CLComputation and Language cs.SESoftware Engineering

On Hacker News

Linked by 3 identifiable commenters in 3 comments across 3 threads, from Aug 2018 to Sep 2026. Found in 1 HN submission from Feb 2018 to Feb 2018. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments3 threads

  1. Show HN: TERMy – A fast terminal assistant that does not use LLMs 1 comment
  2. OpenAI API 1 comment

    • Cool indeed! While language-to-code (where code is a regular, general-purpose language) has only recently started to be workable, text-to-SQL has been a long running application/research area for semantic parsing. Some interesting papers and datasets: NL2Bash…

      nickswalkerView on HNParent context

  3. NL2Bash – Generating bash commands from natural language 1 comment

    • It was mentioned in the paper (https://arxiv.org/abs/1802.08979): commands that correspond to non-Bash language interpreters were filtered out from the dataset and `awk` and `sed` were filtered out because they are the interpreters of string processing languages.

      todpole3View on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.