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

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 Salesforce Research, University of Washington, University of Washington, University of Washington xilin@salesforce.com, {clwang,lsz,mernst}@cs.washington.edu 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. Keywords: Natural Language Programming, Natural Language Interface, Semantic Parsing 1. Introduction The dream of using English or any other natural language to program computers has existed for almost as long as the task of programming itself (Sammet, 1966). Although significantly less precise than a formal language (Dijkstra, 1978), natural language as a programming medium would be universally accessible and would support the automation of highly repetitive tasks such as file manipulation, search, and application-specific scripting (Wilensky et al., 1984; Wilensky et al., 1988; Dahl et al., 1994; Quirk et al., 2015; Desai et al., 2016). This work presents new data and semantic parsing meth- ods on a novel and ambitious domain — natural language control of the operating system. Our long-term goal is to enable any user to perform tasks on their computers by sim- ply stating their goals in natural language (NL). We take a first step in this direction, by providing a large new dataset (NL2Bash) of challenging but commonly used commands and expert-written descriptions, along with baseline methods to establish performance levels on this task. The NL2Bash problem can be seen as a type of semantic parsing, where the goal is to map sentences to formal repre- sentations of their underlying meaning (Mooney, 2014). The dataset we introduce provides a new type of target mean- ing representations (Bash1 commands), and is significantly larger (from two to ten times) than most existing semantic parsing benchmarks (Dahl et al., 1994; Popescu et al., 2003). Other recent work in semantic parsing has also focused on programming languages, including regular expressions (Lo- cascio et al., 2016), IFTTT scripts (Quirk et al., 2015), and SQL queries (Kwiatkowski et al., 2013; Iyer et al., 2017; Zhong et al., 2017). However, the shell command data we consider raises unique challenges, due to its irregular syntax (no syntax tree representation for the command options), wide domain coverage (> 100 Bash utilities), and a large percentage of unseen words (e.g. commands can manipulate arbitrary files). * Work done at the University of Washington. 1The Bourne-again shell (Bash) is the most popular Unix shell and command language: https://www.gnu.org/software/bash/. Our data collection approach and baseline models can be trivially gen- eralized to other command languages. We constructed the NL2Bash corpus with frequently used Bash commands scraped from websites such …

Content truncated to 500 words