Vajra: Step-by-step Programming with Natural Language

Viktor Schlegel; Benedikt Lang; Siegfried Handschuh; Andre Freitas

doi:10.1145/3301275.3302267

Vajra: Step-by-step Programming with Natural Language

Viktor Schlegel, Benedikt Lang, Siegfried Handschuh, Andre Freitas

Information Management

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

311 Downloads (Pure)

Abstract

Building natural language programming systems that are geared towards end-users requires the abstraction of formalisms inherently introduced by programming languages, capturing the intent of natural language inputs and mapping it to existing programming language constructs.
We present a novel end-user programming paradigm for Python, which maps natural language commands into Python code. The proposed semantic parsing model aims to reduce the barriers for producing well-formed code (syntactic gap) and for exploring thirdparty APIs (lexico-semantic gap). The proposed method was implemented in a supporting system and evaluated in a usability study involving programmers as well as non-programmers. The results show that both groups are able to produce code with or without prior programming experience.

Original language	English
Title of host publication	IUI '19: Proceedings of the 24th International Conference on Intelligent User Interfaces
Publisher	ACM Digital Library
ISBN (Print)	978-1-4503-6272-6
DOIs	https://doi.org/10.1145/3301275.3302267
Publication status	Published - Mar 2019
Event	24th International Conference on Intelligent User Interfaces - Los Angeles, United States Duration: 17 Mar 2019 → 20 Mar 2019

Conference

Conference	24th International Conference on Intelligent User Interfaces
Abbreviated title	ACM IUI 2019
Country/Territory	United States
City	Los Angeles
Period	17/03/19 → 20/03/19

Keywords

interactive programming
end-user programming
semantic parsing
IDEs
novice programmers

Access to Document

10.1145/3301275.3302267

IUI_2019__VajraAccepted author manuscript, 960 KB

Cite this

@inproceedings{f615488ad71a4fd898c2297acdde3dad,

title = "Vajra: Step-by-step Programming with Natural Language",

abstract = "Building natural language programming systems that are geared towards end-users requires the abstraction of formalisms inherently introduced by programming languages, capturing the intent of natural language inputs and mapping it to existing programming language constructs.We present a novel end-user programming paradigm for Python, which maps natural language commands into Python code. The proposed semantic parsing model aims to reduce the barriers for producing well-formed code (syntactic gap) and for exploring thirdparty APIs (lexico-semantic gap). The proposed method was implemented in a supporting system and evaluated in a usability study involving programmers as well as non-programmers. The results show that both groups are able to produce code with or without prior programming experience.",

keywords = "interactive programming, end-user programming, semantic parsing, IDEs, novice programmers",

author = "Viktor Schlegel and Benedikt Lang and Siegfried Handschuh and Andre Freitas",

year = "2019",

month = mar,

doi = "10.1145/3301275.3302267",

language = "English",

isbn = "978-1-4503-6272-6",

booktitle = "IUI '19: Proceedings of the 24th International Conference on Intelligent User Interfaces",

publisher = "ACM Digital Library",

address = "United States",

note = "24th International Conference on Intelligent User Interfaces , ACM IUI 2019 ; Conference date: 17-03-2019 Through 20-03-2019",

}

TY - GEN

T1 - Vajra: Step-by-step Programming with Natural Language

AU - Schlegel, Viktor

AU - Lang, Benedikt

AU - Handschuh, Siegfried

AU - Freitas, Andre

PY - 2019/3

Y1 - 2019/3

N2 - Building natural language programming systems that are geared towards end-users requires the abstraction of formalisms inherently introduced by programming languages, capturing the intent of natural language inputs and mapping it to existing programming language constructs.We present a novel end-user programming paradigm for Python, which maps natural language commands into Python code. The proposed semantic parsing model aims to reduce the barriers for producing well-formed code (syntactic gap) and for exploring thirdparty APIs (lexico-semantic gap). The proposed method was implemented in a supporting system and evaluated in a usability study involving programmers as well as non-programmers. The results show that both groups are able to produce code with or without prior programming experience.

AB - Building natural language programming systems that are geared towards end-users requires the abstraction of formalisms inherently introduced by programming languages, capturing the intent of natural language inputs and mapping it to existing programming language constructs.We present a novel end-user programming paradigm for Python, which maps natural language commands into Python code. The proposed semantic parsing model aims to reduce the barriers for producing well-formed code (syntactic gap) and for exploring thirdparty APIs (lexico-semantic gap). The proposed method was implemented in a supporting system and evaluated in a usability study involving programmers as well as non-programmers. The results show that both groups are able to produce code with or without prior programming experience.

KW - interactive programming

KW - end-user programming

KW - semantic parsing

KW - IDEs

KW - novice programmers

U2 - 10.1145/3301275.3302267

DO - 10.1145/3301275.3302267

M3 - Conference contribution

SN - 978-1-4503-6272-6

BT - IUI '19: Proceedings of the 24th International Conference on Intelligent User Interfaces

PB - ACM Digital Library

T2 - 24th International Conference on Intelligent User Interfaces

Y2 - 17 March 2019 through 20 March 2019

ER -

Vajra: Step-by-step Programming with Natural Language

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this