Logo des Repositoriums

Auflistung nach Schlagwort "Natural Language"

1 - 2 von 2
  • Zeitschriftenartikel
    Design Thinking: Ein Videoprojekt zu Computing with Words schlägt neue Brücken zwischen Forschung und Praxis
    (HMD Praxis der Wirtschaftsinformatik: Vol. 55, No. 3, 2018) D’Onofrio, Sara; Tschudi, Fabrice
    Die digitale Welt wächst exponentiell und dringt immer tiefer ins menschliche Leben vor. Dieser Artikel befasst sich im Bereich Mensch-Maschine-Interaktion mit menschenzentrierten Innovationsprozessen und der Zusammenarbeit von Forschung und Praxis. Im soeben erwähnten Bereich ist die Technik Computing with Words Bestandteil dieser Arbeit, ein Ansatz der grosse und heterogen-strukturierte Datenmengen verarbeiten und auf die Bearbeitung von natürlichen Sprachen vorbereiten soll. Am Beispiel dieser von menschlichen Denkprozessen herrührenden Technik wird veranschaulicht, wie mit der Methode Design Thinking die Entwicklung von Videoprotoypen dazu verwendet werden kann, die Zusammenarbeit zwischen Forschung und Praxis voranzutreiben. Dabei wird diese Methode als Chance herausgestrichen, Forschung und Praxis für eine längerfristige Kollaboration zusammenzubringen. Das Resultat dieses ersten Versuchs Brücken zwischen beiden Parteien zu schlagen sind zwei Videos im Bereich Web-Analyse und Monitoring, welche auf YouTube mit den Suchbegriffen „(1/2) Introducing: Computing with Words and Perceptions“ und „(2/2) Computing with Words: How it works“ gefunden werden können. The digital world is growing exponentially and reaching ever deeper into human life. This article is, in the domain of human-computer-interaction, about human-centered innovation processes as well as about the cooperation between scientific research and practice. In the just mentioned domain the technique of computing with words is included in this article, an approach that is meant to process large and heterogenic-structured data and thus to prepare for dealing with natural languages. At the example of this technique that was inspired by human thinking processes it is shown, how the development of video prototypes by the method of design thinking can be used for driving the collaboration between scientific research and practice forward. Thereby, this method is identified as opportunity to unite scientific research and practice for collaboration on a fairly long-term basis. The result of this first attempt of building bridges between both parties are two videos in the area of web-analysis and monitoring, which can be found on YouTube by searching “(1/2) Introducing: Computing with Words and Perceptions” and “(2/2) Computing with Words: How it works”.
  • ConferencePaper
    Trace Link Recovery Using Semantic Relation Graphs and Spreading Activation
    (Software Engineering 2021, 2021) Schlutter, Aaron; Vogelsang, Andreas
    The paper was first published at the 28th IEEE International Requirements Engineering Conference in 2020. Trace Link Recovery tries to identify and link related existing requirements with each other to support further engineering tasks. Existing approaches are mainly based on algebraic Information Retrieval or machine-learning. Machine-learning approaches usually demand reasonably large and labeled datasets to train. Algebraic Information Retrieval approaches like distance between tf-idf scores also work on smaller datasets without training but are limited in providing explanations for trace links. In this work, we present a Trace Link Recovery approach that is based on an explicit representation of the content of requirements as a semantic relation graph and uses Spreading Activation to answer trace queries over this graph. Our approach is fully automated including an NLP pipeline to transform unrestricted natural language requirements into a graph. We evaluate our approach on five common datasets. Depending on the selected configuration, the predictive power strongly varies. With the best tested configuration, the approach achieves a mean average precision of 40% and a Lag of 50%. Even though the predictive power of our approach does not outperform state-of-the-art approaches, we think that an explicit knowledge representation is an interesting artifact to explore in Trace Link Recovery approaches to generate explanations and refine results.