Semantic Enriching of Natural Language Texts with Automatic Thematic Role Annotation
S. Körner, and M. Landhäußer. International Conference on Applications of Natural Language to Information Systems, NLDB 2010,Cardiff, UK, June 23-25, volume 6177 of Lecture Notes in Computer Science, page 92--99. Berlin, Heidelberg, Springer, (July 2010)
This paper proposes an approach which utilizes natural language processing (NLP) and ontology knowledge to automatically denote the implicit semantics of textual requirements. Requirements documents include the syntax of natural language but not the semantics. Semantics are usually interpreted by the human user. In earlier work Gelhausen and Tichy showed that SaleMX automatically creates UML domain models from (semantically) annotated textual specifications. This manual annotation process is very time consuming and can only be carried out by annotation experts. We automate semantic annotation so that SaleMX can be completely automated. With our approach, the analyst receives the domain model of a requirements specification in a very fast and easy manner. Using these concepts is the first step into farther automation of requirements engineering and software development.