Semantic Enriching of Natural Language Texts with Automatic Thematic Role Annotation

  • Tagung:

    Konferenzartikel 

  • Autoren:

    Sven J. Körner
    Mathias Landhäußer     

  • Summary

    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 andTichy 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 ofrequirements engineering and software development.
  • Jahr:

    2010 

  • Links:
Beteiligte Mitarbeiter (zufällige Reihenfolge)
Titel Vorname Nachname
Dr. Sven J. Körner
Dr. Mathias Landhäußer

Bibtex

@inproceedings{,
author={Sven J. K{\"o}rner, Mathias Landh{\"a}u{\ss}er},
title={Semantic Enriching of Natural Language Texts with Automatic Thematic Role Annotation},
year=2010,
month=Jun,
booktitle={Proceedings of the Natural language processing and information systems, and 15th international conference on Applications of natural language to information systems},
editor={Springer-Verlag},
institution={Cardiff University, Wales, UK},
isbn={3-642-13880-2, 978-3-642-13880-5}, numpages = {8}, url = {http://dl.acm.org/citation.cfm?id=1894525.1894537}, acmid = {1894537},
url={https://ps.ipd.kit.edu/downloads/ka_2010_semantic_enriching_natural_language_texts.pdf},
abstract={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 andTichy 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 ofrequirements engineering and software development.},
organization={NLDB 2010},
pages={92--99},
address={Berlin, Heidelberg},
}