Real-time narrative summaries for NOAA's PORTS®

NOAA's PORTS (R) (Physical Oceanographic Real-Time System) currently provides historical and real-time observations and predictions of water levels, coastal currents and other meteorological and oceanographic data for a dozen us estuaries. PORTS (http://co-ops.nos.noaa.gov/d_ports.html) displays its real-time data in graphical and tabular form. These forms can require lengthy inspection to retrieve the relevant details, particularly in a large PORTS locale with many sensors. ARNS (Automated Real-time Narrative Summaries) complements the tabular display by providing automatically generated natural-language summaries of estuary conditions, in order to give users a more comprehensive overview of the data. ARNS is built using CoGenTex, Inc.'s Exemplars (http://www.cogentex.com/technology/exemplars/index.shtmi), a rule-based, object-oriented framework for dynamic generation of text and hypertext. Unlike earlier rule-based systems used to generate weather forecasts via multi-layered linguistic representations, ARNS relies on Exemplars' provision for linguistically marked "text snippets" which can be maintained and extended by user organizations for a given application without recourse to special linguistic training. NOAA and CoGenTex have designed an Extensible Markup Language (XML) format for input of sensor data to ARNS. Qualitative and quantitative summarizations are done real-time and passed to the text generator via the XML schema. Text summaries are generated in real-time and made available via the internet and in the future will be available via the PORTS (R) voice access system.