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

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.

• Publication year

  2018

• Venue

  International Conference on Language Resources and Evaluation

• Publication date

  2018-02-01

• Fields of study

  Computer Science

• Identifiers
  arXiv 1802.08979
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Neural Program Search: Solving Programming Tasks from Description and Examples

  2018cited by this paper
• Natural Language Processing and Program Analysis for Supporting Todo Comments as Software Evolves

  2018cited by this paper
• Generating Regular Expressions from Natural Language Specifications: Are We There Yet?

  2018cited by this paper
• StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow

  2018cited by this paper
• Program Synthesis from Natural Language Using Recurrent Neural Networks

  2017influential reference
• From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood

  2017cited by this paper
• Learning a Neural Semantic Parser from User Feedback

  2017cited by this paper
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

  2017cited by this paper
• The Value of Semantic Parse Labeling for Knowledge Base Question Answering

  2016cited by this paper
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning

  2016influential reference
• Simpler Context-Dependent Logical Forms via Model Projections

  2016cited by this paper
• Summarizing Source Code using a Neural Attention Model

  2016cited by this paper
• A Corpus and Semantic Parser for Multilingual Natural Language Querying of OpenStreetMap

  2016cited by this paper
• Latent Predictor Networks for Code Generation

  2016cited by this paper
• Language to Logical Form with Neural Attention

  2016cited by this paper
• Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge

  2016cited by this paper
• Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

  2016influential reference
• Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation (T)

  2015cited by this paper
• Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes

  2015cited by this paper
• Program Synthesis Using Natural Language

  2015cited by this paper
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks

  2015influential reference
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

  2014cited by this paper
• Sequence to Sequence Learning with Neural Networks

  2014influential reference
• Large-scale Semantic Parsing via Schema Matching and Lexicon Extension

  2013cited by this paper
• Using Semantic Unification to Generate Regular Expressions from Natural Language

  2013cited by this paper
• Scaling Semantic Parsers with On-the-Fly Ontology Matching

  2013cited by this paper
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

  2005cited by this paper
• Towards a theory of natural language interfaces to databases

  2003cited by this paper
• Automatic evaluation of machine translation quality using n-gram co-occurrence statistics

  2002cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• Using Multiple Clause Constructors in Inductive Logic Programming for Semantic Parsing

  2001cited by this paper
• Recurrent neural networks: design and applications

  1999cited by this paper
• THE LANGUAGE OF LOGICAL FORM

  1999influential reference
• Bidirectional recurrent neural networks

  1997influential reference
• Learning to Parse Database Queries Using Inductive Logic Programming

  1996cited by this paper
• Expanding the Scope of the ATIS Task: The ATIS-3 Corpus

  1994influential reference
• The Berkeley UNIX Consultant Project

  1988cited by this paper
• Talking to UNIX in English: an overview of UC

  1984cited by this paper
• On the Foolishness of "Natural Language Programming"

  1978cited by this paper
• The use of English as a programming language

  1966cited by this paper

• ComAlign: A Benchmark Aligning Natural Language with Operating System Commands

  2026cites this paper
• Endless Terminals: Scaling RL Environments for Terminal Agents

  2026influential citation
• SWE-Universe: Scale Real-World Verifiable Environments to Millions

  2026cites this paper
• Alleviating the Fear of Losing Alignment in LLM Fine-tuning

  2025cites this paper
• Flash: Federated Graph Learning-Based Malicious Bash Script Detection for Industrial Cyber–Physical Systems

  2025cites this paper
• Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Enhancement Protocol

  2025cites this paper
• Bridging the Gap Between Natural Language and CLI: An Intelligent Assistant Approach

  2025cites this paper
• PromptOS: Study of Natural-Language Shells, Execution-Based Evaluation, Command-Syntax Learning, and Runtime Guardrails

  2025cites this paper
• SLMFix: Leveraging Small Language Models for Error Fixing with Reinforcement Learning

  2025cites this paper
• LLM-Supported Natural Language to Bash Translation

  2025cites this paper
• Accessible and Reliable AI Coding Tutors: Augmenting Large Language Models with Retrieval-Augmented Generation for Java Programming

  2025cites this paper
• Large Language Models Often Know When They Are Being Evaluated

  2025influential citation
• Prompt Engineering Techniques for Context-dependent Text-to-SQL in Arabic

  2025cites this paper
• Natural Language to Bash Command Translation Using Large Language Models with Agentic External Tool Feedback

  2025cites this paper
• Correlation-Aware Example Selection for In-Context Learning with Nonsymmetric Determinantal Point Processes

  2025cites this paper
• Generative Caching for Structurally Similar Prompts and Responses

  2025cites this paper
• Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality

  2025cites this paper
• Learning "Partner-Aware" Collaborators in Multi-Party Collaboration

  2025cites this paper
• The Command Line GUIde: Graphical Interfaces from Man Pages via AI

  2025cites this paper
• Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language Agents

  2025cites this paper
• Good Vibrations? A Qualitative Study of Co-Creation, Communication, Flow, and Trust in Vibe Coding

  2025cites this paper
• SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments

  2025cites this paper
• ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation

  2025cites this paper
• DABstep: Data Agent Benchmark for Multi-step Reasoning

  2025cites this paper
• Automatic Grading of Linux Commands Using String Similarity Measures

  2025influential citation
• Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching

  2025cites this paper
• ShIOEnv: A Command Evaluation Environment for Grammar-Constrained Synthesis and Execution Behavior Modeling

  2025cites this paper
• Mapping the Landscape of Generative AI in Network Monitoring and Management

  2025cites this paper
• Robust Synthetic Data-Driven Detection of Living-Off-the-Land Reverse Shells

  2024cites this paper
• Soft Self-Consistency Improves Language Model Agents

  2024cites this paper
• Condor: A Code Discriminator Integrating General Semantics With Code Details

  2024cites this paper
• LLM-based Optimization of Compound AI Systems: A Survey

  2024cites this paper
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

  2024cites this paper
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

  2024cites this paper
• SpiderScan: Practical Detection of Malicious NPM Packages Based on Graph-Based Behavior Modeling and Matching

  2024cites this paper
• DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models

  2024cites this paper
• Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback

  2024cites this paper
• Automatic regex synthesis methods for english: a comparative analysis

  2024cites this paper
• Don’t Stop Believin’: A Unified Evaluation Approach for LLM Honeypots

  2024influential citation
• ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement

  2024cites this paper
• Contextualized Data-Wrangling Code Generation in Computational Notebooks

  2024cites this paper
• Hierarchical Programmatic Option Framework

  2024cites this paper
• Bash comment generation via data augmentation and semantic-aware CodeBERT

  2024influential citation
• In-context Learning with Retrieved Demonstrations for Language Models: A Survey

  2024cites this paper
• NICE: To Optimize In-Context Examples or Not?

  2024cites this paper
• AssistGUI: Task-Oriented PC Graphical User Interface Automation

  2024cites this paper
• RACONTEUR: A Knowledgeable, Insightful, and Portable LLM-Powered Shell Command Explainer

  2024cites this paper
• HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model

  2024cites this paper
• Structure and design of multimodal dataset for automatic regex synthesis methods in Roman Urdu

  2024cites this paper
• Mixture of Demonstrations for In-Context Learning

  2024cites this paper
• PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning

  2024cites this paper
• DocCGen: Document-based Controlled Code Generation

  2024cites this paper
• Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning

  2024cites this paper
• Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases

  2024cites this paper
• On the Noise Robustness of In-Context Learning for Text Generation

  2024influential citation
• Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search

  2024cites this paper
• Distantly Supervised Contrastive Learning for Low-Resource Scripting Language Summarization

  2024cites this paper
• SpreadNaLa: A Naturalistic Code Generation Evaluation Dataset of Spreadsheet Formulas

  2024cites this paper
• NL2CMD: An Updated Workflow for Natural Language to Bash Commands Translation

  2023cites this paper
• Augmented Embeddings for Custom Retrievals

  2023cites this paper
• Naturalistic Static Program Analysis

  2023cites this paper
• Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs

  2023cites this paper
• Compositional Exemplars for In-context Learning

  2023cites this paper
• LEVER: Learning to Verify Language-to-Code Generation with Execution

  2023cites this paper
• Learning Deep Semantics for Test Completion

  2023cites this paper
• Hierarchical Neural Program Synthesis

  2023influential citation
• NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions

  2023cites this paper
• FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information

  2023cites this paper
• SPARQL-QA-v2 system for Knowledge Base Question Answering

  2023cites this paper
• Neural Machine Translation for Code Generation

  2023cites this paper
• Generating Data for Symbolic Language with Large Language Models

  2023cites this paper
• ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games

  2023cites this paper
• Facilitating Software Evolution through Natural Language Comments and Dialogue

  2023cites this paper
• InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback

  2023influential citation
• ShellFusion: An Answer Generator for Shell Programming Tasks via Knowledge Fusion

  2023cites this paper
• LogPrécis: Unleashing Language Models for Automated Shell Log Analysis

  2023influential citation
• AgentBench: Evaluating LLMs as Agents

  2023cites this paper
• Automatic Synthesis of Network Security Services: A First Step

  2023cites this paper
• A Survey of Detection Methods Research on Living-Off-The-Land Techniques

  2023cites this paper
• LogPrécis: Unleashing language models for automated malicious log analysis

  2023cites this paper
• Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines

  2023cites this paper
• ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation

  2023cites this paper
• Dynamic Retrieval-Augmented Generation

  2023cites this paper
• Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models

  2023cites this paper
• Agent Lumos: Unified and Modular Training for Open-Source Language Agents

  2023cites this paper
• ShellGPT: Generative Pre-trained Transformer Model for Shell Language Understanding

  2023cites this paper
• Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey

  2023cites this paper
• CodeFusion: A Pre-trained Diffusion Model for Code Generation

  2023influential citation
• Bash in the Wild: Language Usage, Code Smells, and Bugs

  2023influential citation
• TSTR: Target Similarity Tuning Meets the Real World

  2023cites this paper
• Anomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Approaches

  2023cites this paper
• Coder Reviewer Reranking for Code Generation

  2022cites this paper
• A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective

  2022influential citation
• DualSC: Automatic Generation and Summarization of Shellcode via Transformer and Dual Learning

  2022cites this paper
• UniSAr: a unified structure-aware autoregressive language model for text-to-SQL semantic parsing

  2022cites this paper
• Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation

  2022cites this paper
• Enabling Near Real-Time NLU-Driven Natural Language Programming through Dynamic Grammar Graph-Based Translation

  2022cites this paper
• Translating Natural Language to Bash Commands using Deep Neural Networks

  2022cites this paper
• Natural Language to Code Translation with Execution

  2022influential citation
• Stylette: Styling the Web with Natural Language

  2022cites this paper