SemScribe

From NLG Systems Wiki

Jump to: navigation, search

[edit] Summary

  • System Name: SemScribe
  • Short Description: SemScribe is an implemented natural language generation system that produces parts of clinical reports, in particular descriptions of cardiological findings.
  • System Builders: Manfred Stede, Heike Bieler, Sebastian Varges, Peter Kolb, Lukas C. Faulstich, Kristin Irsig, Malik Atalla[1]
  • Development Period: 2010–2011
  • Languages: German
  • Domain: Medical (cardiology)

Description

Natural language generation in the medical domain is heavily influenced by domain knowledge and genre-specific text characteristics. SemScribe is an implemented natural language generation system that produces parts of clinical reports, in particular descriptions of cardiological findings. Texts in this domain are characterized by a high density of information and a relatively telegraphic style. Domain knowledge is encoded in a medical ontology of about 80,000 concepts. The ontology is used in particular for concept generalizations during referring expression generation. Architecturally, the system is a generation pipeline that uses a corpus-informed syntactic frame approach for realizing sentences appropriate to the domain.

References

  1. Faulstich, L. C., Irsig, K., Atalla, M., Varges, S., Bieler, H., & Stede, M. (2011). SemScribe: Automatic Generation of Medical Reports. Paper presented at Proceedings of USAB 2011 – Information Quality in eHealth. Bib
Facts about SemScribeRDF feed
DescriptionSemScribe is an implemented natural language generation system that produces parts of clinical reports, in particular descriptions of cardiological findings.  +
DomainMedical (cardiology)  +
Ended2011  +
NameSemScribe  +
Started2010  +
Personal tools