English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Systems engineering, in particular in the automotive domain, needs to copewith the massively increasing numbers of requirements that arise during thedevelopment process. To guarantee a high product quality and make sure thatfunctional safety standards such as ISO26262 are fulfilled, the exploitation ofpotentials of model-driven systems engineering in the form of automaticanalyses, consistency checks, and tracing mechanisms is indispensable. However,the language in which requirements are written, and the tools needed to operateon them, are highly individual and require domain-specific tailoring. Thishinders automated processing of requirements as well as the linking ofrequirements to models. Introducing formal requirement notations in existingprojects leads to the challenge of translating masses of requirements andprocess changes on the one hand and to the necessity of the correspondingtraining for the requirements engineers.  In this paper, based on the analysis of an open-source set of automotiverequirements, we derive domain-specific language constructs helping us to avoidambiguities in requirements and increase the level of formality. The maincontribution is the adoption and evaluation of few-shot learning with largepretrained language models for the automated translation of informalrequirements to structured languages such as a requirement DSL. We show thatsupport sets of less than ten translation examples can suffice to few-shottrain a language model to incorporate keywords and implement syntactic rulesinto informal natural language requirements.

Technical Report on Neural Language Models and Few-Shot Learning for Systematic Requirements Processing in MDSE