Kostanyan, Arkadiy V.Shekhovtsov, Vladimir A.Mayr, Heinrich C.Karagiannis, Dimitris2019-05-152019-05-152007978-3-88579-2017https://dl.gi.de/handle/20.500.12116/22690This paper presents our views towards constructing the universal parsing technique for the software requirements texts and the requirements elicitation technique based on the output of this parsing process. With the proposed parsing technique, it should be possible to achieve language-independent processing of the requirements texts. Source sentences are treated as systems with words as elements and with a state determining the set of links between elements. The main goal of the parser is to find the state of the system with the highest organization level by minimizing its entropy. The requirements elicitation technique extends trained indicator approach by Cleland-Huang treating inter-word links as indicators. The output of the elicitation process is the set of requirements information ready to be processed further using Conceptual and Aspectual Predesign techniques.enNLP methodsparsingaspectual predesignconceptual predesigngenetic algorithmentropytrainingindicator weightsText/Conference Paper1617-5468