SUMTIME-MOUSAM: Configurable Marine Weather Forecast Generator

Numerical weather prediction (NWP) models produce time series data of basic weather parameters which human forecasters use as guidance while writing textual forecasts. Our studies of humans writing textual weather forecasts led us to build SUMTIME-MOUSAM, a text generator that produces textual marine weather forecasts for offshore oilrig applications. SUMTIME-MOUSAM separates control and processing. As a result of this forecasters can tailor the output text using control data derived from end user profiles. In this paper we describe the design and the implementation details of SUMTIME-MOUSAM which is currently being used by our industrial collaborator. Output from our system is post-edited by forecasters before communicating it to the end-users. We also briefly describe an evaluation of our system using the post-edit data.