Back to search

Georgia Institute of Technology

Generation of Linux commands using natural language descriptions

Abstract

dc:description.abstract

Translating natural language into source code or programs is an important problem in natural language understanding -- both in terms of practical applications and in terms of understanding usage of language to affect action. In this domain, we consider the problem of translating natural language descriptions of LINUX commands into the corresponding commands. This is useful from the point of view of users who want to get commands executed but lack expertise to come up with them on the bash terminal. The major contribution of this thesis is a parallel corpus for translating natural language into LINUX commands. The corpus contains 4561 unique commands and 3-4 descriptions for each command, making a total of 11177 pairs. Along with the corpus, simple classification settings using Support Vector Machines and translation settings using Sequence to Sequence Recurrent Neural Network based models are studied to provide benchmarks for machine learning model performance on the collected dataset. This document provides analysis of the collected dataset, and describes the results and findings from models trained on the dataset.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Computer Science
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2018

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Raval, Ananya
Advisor dc:contributor.advisor
  • Parikh, Devi
Committee members dc:contributor.committeemember
  • Batra, Dhruv
  • Chau, Duen Horng (Polo)

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/59849

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Raval, Ananya. Generation of Linux commands using natural language descriptions. Masters thesis, Georgia Institute of Technology, 2018. http://hdl.handle.net/1853/59849