Automatically generating natural language status reports

Jugal Kalita, Sunil Shende

Research output: Contribution to journalArticlepeer-review


In this paper, we describe a system which generates compact natural language status reports for a set of inter-related processes at various stages of progress. The system has three modules - a rule-based domain knowledge representation module, an elaborate text planning module, and a surface generation module. The knowledge representation module models a set of processes that are encountered in a typical office environment, using a body of explicitly sequenced production rules implemented by an augmented Petri net mechanism. The system employs an interval-based temporal network for storing historical information. A text planning module traverses this network to search for events which need to be mentioned in a coherent report describing the current status of the system. The planner combines similar information for succinct presentation whenever applicable. It also takes into consideration various issues such as relevance and redundancy, simple mechanisms for viewing events from multiple perspectives and the application of discourse focus techniques for the generation of good quality text. Finally, an available surface generation module which has been suitably augmented is used to produce well-structured textual reports for our chosen domain.

Original languageAmerican English
Pages (from-to)533-540
Number of pages8
JournalProceedings of SPIE - The International Society for Optical Engineering
StatePublished - Mar 29 1988
Externally publishedYes

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Automatically generating natural language status reports'. Together they form a unique fingerprint.

Cite this