Toward leveraging Gherkin Controlled Natural Language and Machine Translation for Global Product Information Development

2862

Authors

nan

Abstract

AbstractMachine Translation (MT) already plays an important part in software development process at McAfee where the technology can be leveraged to provide early builds for localization and internationalization testing teams. Behavior Driven Development (BDD) has been growing in usage as a development methodology in McAfee. Within BDD, the Gherkin Controlled Natural Language (CNL) is a syntax and common terminology set that is used to describe the software or business process in a User Story. Given there exists this control on the language to describe User Stories for software features using Gherkin, we seek to use Machine Translation to Globalize it at high accuracy and without PostEditing and reuse it as Product Information. This enables global product information development to happen as part of the Software Development Life Cycle (SDLC) and at low cost.

Keywords

nan

Full Content

Toward leveraging Gherkin Controlled Natural Language and Ma- chine Translation for Global Product Information Development Morgan O’Brien McAfee, Building 2000 Citygate, Mahon, Cork mobrien@mcafee.com Abstract Machine Translation (MT) already plays an important part in software develop- ment process at McAfee where the tech- nology can be leveraged to provide early builds for localization and internationali- zation testing teams. Behavior Driven Development (BDD) has been growing in usage as a develop- ment methodology in McAfee. Within BDD, the Gherkin Controlled Natural Language (CNL) is a syntax and com- mon terminology set that is used to de- scribe the software or business process in a User Story. Given there exists this control on the language to describe User Stories for software features using Gherkin, we seek to use Machine Translation to Globalize it at high accuracy and without Post- Editing and reuse it as Product Infor- mation. This enables global product in- formation development to happen as part of the Software Development Life Cycle (SDLC) and at low cost. __________________ © 2018 Morgan O’Brien, McAfee LLC. 1 Credits This document is based on the understanding that commercial Machine Translation systems per- form well when used in conjunctions with Con- trolled Language rules (Roturier, 2004). It uses Gherkin CNL as written by developers and test- ers of McAfee products. The Machine Transla- tion system used are from the Microsoft Transla- tor Hub. The paper takes input from Information Development teams in McAfee based on the style and standards that they have in place. 2 Introduction BDD is fast becoming a standard in software development, especially where the User Interface is primarily web based. It aims to satisfy needs of customers in software design by representing the behavior of the user as part of the plan. Using the Gherkin CNL, which is designed to work with BDD frameworks, a business manager who is not a developer can quickly describe how the software should function using examples. Example based learning has advantages for understanding and retention of information. It enhances the effectiveness of User Stories in Agile software development by reducing ambiguity and enabling non-technical personnel to be involved. It also enhances the ability for a person to retain the information better by the application of a cognitive load to the user as they read. Gherkin could possibly be used as a superior learning asset to traditional information development for complex software processes by virtue that the reader employs more mental effort as they read which helps them retain the information better. In McAfee, software design is managed through JIRA, a tool for planning, tracking and managing Agile software development. Gherkin descriptions are not currently part of that system and are rarely shared outside of the software Development and Testing teams. By accessing the test code, we get access to the Gherkin which in turn can facilitate the future possibilities such as Information Development. In turn, the ability to quickly leverage this content for international markets at low cost is an attractive possibility for the …

Content truncated to 500 words

Labeled Text

AbstractMachine Translation (MT) already plays an important part in software development process at McAfee where the technology can be leveraged to provide early builds for localization and internationalization testing teams. Behavior Driven Development (BDD) has been growing in usage as a development methodology in McAfee. Within BDD, the Gherkin Controlled Natural Language (CNL) is a syntax and common terminology set that is used to describe the software or business process in a User Story. Given there exists this control on the language to describe User Stories for software features using Gherkin, we seek to use Machine Translation to Globalize it at high accuracy and without PostEditing and reuse it as Product Information. This enables global product information development to happen as part of the Software Development Life Cycle (SDLC) and at low cost.

Publication Details

Paper ID:
2862
Year:
2018
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan