Flexible Ambiguity Resolution and Incompleteness Detection in Requirements Descriptions via an Indicator-Based Configuration of Text Analysis Pipelines

Abstract

Naturallanguage software requirements descriptions enable end users to formulate their wishes and expectations for a future software product without much prior knowledge in requirements engineering. However, these descriptions are susceptible to linguistic inaccuracies such as ambiguities and incompleteness that can harm the development process. There is a number of software solutions that can detect deficits in requirements descriptions and partially solve them, but they are often hard to use and not suitable for end users. For this reason, we develop a software system that helps end-users to create unambiguous and complete requirements descriptions by combining existing expert tools and controlling them using automatic compensation strategies.In order to recognize the necessity of individual compensation methods in the descriptions, we have developed linguistic indicators, which we present in this paper. Based on these indicators, the whole text analysis pipeline is ad-hoc configured and thus adapted to the individual circumstances of a requirements description.

Natural Language Processing in OTF Computing: Challenges and the Need for Interactive Approaches

“…Thus, end users have to be informed in order to understand the service composition and be satisfied with its characteristics. So far, corrections are in part highlighted or compared to the input (e.g., [19]); however, there is no explanation information for the changes. There are several challenges in the OTF context: the NL input of end users mainly shapes the software composition even though the type of composition (the actual software service selection step) has an influence as well.…”

“…The disambiguation service Babelfy is often used as a substitute for a domain-specific disambiguation but is hosted entirely on external servers [17,18]. Despite good performance [19], server failures, network errors and response times would be a threat when integrating this service in a live OTF Computing system [8]. In addition, the integration of third-party software oftentimes does not work, due to a lack of programming interfaces, but is crucial for an automatic and quick system.…”

Requirements Smells como indicadores de má qualidade na especificação de requisitos: Um Mapeamento Sistemático da Literatura

“…No trabalho de [20], baseado na ISO 29148, foi descrito que são sintomas de defeitos na qualidade de requisitos. Nos trabalhos de [7,41] foi descrito que são sinais de deficiência em requisitos e um concreto sintoma para defeito de qualidade. Nos trabalhos [5,12] foi descrito que podem ser sinais de imprecisão ou ambiguidade na declaração de requisitos, causando alto custo de refatoração.…”

“…Nos trabalhos [5,12] foi descrito que podem ser sinais de imprecisão ou ambiguidade na declaração de requisitos, causando alto custo de refatoração. Nos trabalhos de [7,8,21], Requirements Smells foi definido de forma mais detalhada e contextualizada, onde estas anomalias são caracterizadas por:…”

“…A ferramenta foi utilizada para detectar problemas de qualidade em documentos de requisitos como: Vague Terms, Passive Voice, Missing Reference, Modal Adverbs, Anaphoric Ambiguity, Non-verifiable Terms e Coordination Ambiguity. Em [7] foi proposto um protótipo ferramental, onde o usuário especifica requisitos em linguagem natural e através de PLN, é realizada uma análise para detectar erros e pontos fracos relacionados à ambiguidade e incompletude nos requisitos baseado em [20].…”