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.

cs.CL cs.SE Computer Science

Paper

References (49)

01StaQC: A Systematically Mined Question-Code Dataset from Stack OverflowZiyu Yao, Daniel S. Weld, Wei-Peng Chen et al.2018 · The Web Conference · 113 citations In Library

02Neural Program Search: Solving Programming Tasks from Description and ExamplesI. Polosukhin, Alexander Skidanov2018 · International Conference on Learning Representations · 59 citations In Library

03Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement LearningVictor Zhong, Caiming Xiong, R. Socher2017 · arXiv.org · 1.6k citations In Library

04Learning a Neural Semantic Parser from User FeedbackSrini Iyer, Ioannis Konstas, Alvin Cheung et al.2017 · Annual Meeting of the Association for Computational Linguistics · 377 citations In Library

05From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal LikelihoodKelvin Guu, Panupong Pasupat, E. Liu et al.2017 · Annual Meeting of the Association for Computational Linguistics · 199 citations In Library

06Neural Generation of Regular Expressions from Natural Language with Minimal Domain KnowledgeN. Locascio, Karthik Narasimhan, E. DeLeon et al.2016 · Conference on Empirical Methods in Natural Language Processing · 96 citations In Library

07The Value of Semantic Parse Labeling for Knowledge Base Question AnsweringWen-tau Yih, Matthew Richardson, Christopher Meek et al.2016 · Annual Meeting of the Association for Computational Linguistics · 734 citations

08Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)Katrin Erk, Noah A. Smith2016 · Annual Meeting of the Association for Computational Linguistics · 1.4k citations

09Summarizing Source Code using a Neural Attention ModelSrini Iyer, Ioannis Konstas, Alvin Cheung et al.2016 · Annual Meeting of the Association for Computational Linguistics · 787 citations

10Simpler Context-Dependent Logical Forms via Model ProjectionsR. Long, Panupong Pasupat, Percy Liang2016 · Annual Meeting of the Association for Computational Linguistics · 106 citations In Library

11A Corpus and Semantic Parser for Multilingual Natural Language Querying of OpenStreetMapCarolin (Haas) Lawrence, S. Riezler2016 · North American Chapter of the Association for Computational Linguistics · 35 citations

12Latent Predictor Networks for Code GenerationWang Ling, Phil Blunsom, Edward Grefenstette et al.2016 · Annual Meeting of the Association for Computational Linguistics · 410 citations In Library

Scroll for more · 37 remaining

Similar papers

NL2CMD: An Updated Workflow for Natural Language to Bash Commands TranslationQuchen Fu, Zhongwei Teng, Marco Georgaklis et al.2023 · arXiv (Cornell University) In Library

LLM-Supported Natural Language to Bash TranslationFinnian Westenfelder, Erik Hemberg, Miguel Tulla et al.2025 · arXiv (Cornell University) · 13 citations In Library

Natural Language to Bash Command Translation Using Large Language Models with Agentic External Tool FeedbackMehmet Eren Yeşilyurt, Ömer Özgür Tanrıöver2025 In Library

NeurIPS 2020 NLC2CMD Competition: Translating Natural Language to Bash CommandsMayank Agarwal, Tathagata Chakraborti, Quchen Fu et al.2021 · arXiv (Cornell University) · 20 citations In Library

A Transformer-based Approach for Translating Natural Language to Bash CommandsQuchen Fu, Zhongwei Teng, Jules White et al.2021 · 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) · 13 citations In Library

Structural Transfer Learning in NL-to-Bash Semantic ParsersKyle Duffy, Satwik Bhattamishra, Phil Blunsom2023 · arXiv (Cornell University) · 0 citations In Library

PromptOS: Study of Natural-Language Shells, Execution-Based Evaluation, Command-Syntax Learning, and Runtime GuardrailsMihir Ponkshe, Avaneesh Pharande, Vaidehi Bawane et al.2025 In Library

Shell Language Processing: Unix command parsing for Machine LearningDmitrijs Trizna2021 · arXiv.org · 15 citations In Library

Explainable Natural Language to Bash Translation using Abstract Syntax TreeShikhar Bharadwaj, Shirish Shevade2021 In Library

Efficient Constituency Tree based Encoding for Natural Language to Bash TranslationShikhar Bharadwaj, Shirish Shevade2022 · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · 5 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal