no code implementations • 13 Dec 2022 • Jannik Fischbach, Max Adam, Victor Dzhagatspanyan, Daniel Mendez, Julian Frattini, Oleksandr Kosenkov, Parisa Elahidoost
Second, we present our tool-supported approach called ESG-Miner capable of analyzing and evaluating headlines on corporate ESG-performance automatically.
1 code implementation • 2 Aug 2021 • Pablo Restrepo Henao, Jannik Fischbach, Dominik Spies, Julian Frattini, Andreas Vogelsang
In this paper, we investigate the potential of transfer learning (TL) for the classification of user comments.
no code implementations • 21 Jul 2021 • Noah Jadallah, Jannik Fischbach, Julian Frattini, Andreas Vogelsang
Causal relations (If A, then B) are prevalent in requirements artifacts.
1 code implementation • 21 Jul 2021 • Jannik Fischbach, Tobias Springer, Julian Frattini, Henning Femmer, Andreas Vogelsang, Daniel Mendez
Our approach is capable of recovering the composition of causal statements written in natural language and achieves a F1 score of 74 % in the evaluation on the Causality Treebank.
no code implementations • 11 Mar 2021 • Jannik Fischbach, Julian Frattini, Andreas Vogelsang
Requirements often specify the expected system behavior by using causal relations (e. g., If A, then B).
Software Engineering
1 code implementation • 26 Jan 2021 • Jannik Fischbach, Julian Frattini, Arjen Spaans, Maximilian Kummeth, Andreas Vogelsang, Daniel Mendez, Michael Unterkalmsteiner
Our case study corroborates, among other things, that causality is, in fact, a widely used linguistic pattern to describe system behavior, as about a third of the analyzed sentences are causal.
Software Engineering
no code implementations • 29 Jun 2020 • Jannik Fischbach, Benedikt Hauptmann, Lukas Konwitschny, Dominik Spies, Andreas Vogelsang
In this paper, we describe first steps towards building a new approach for causality extraction and contribute: (1) an NLP architecture based on Tree Recursive Neural Networks (TRNN) that we will train to identify causal relations in NL requirements and (2) an annotation scheme and a dataset that is suitable for training TRNNs.
no code implementations • 22 Aug 2019 • Jannik Fischbach, Maximilian Junker, Andreas Vogelsang, Dietmar Freudenstein
[Contribution:] We make three contributions: (1) an algorithm for the automatic detection of semi-structured requirements descriptions in documents, (2) an algorithm for the automatic translation of the identified requirements into a CEG and (3) a study demonstrating that our proposed solution leads to 86 % time savings for test model creation without loss of quality.