<?xml version="1.0" standalone="yes"?>
<Paper uid="C86-1132">
  <Title>VALID UNTIL MIDNIGHT TUESDAY WITH AN OUTLOOK FOR WEDNESDAY. FROBISHER-BAY GALE WARNING ISSUED ... WINDS LIGHT BECOMING SOUTHEASTERLY 15 EAKLY TUESDAY MORNING THEN BACKING AND STRENGTHEN- ING TO EASTERLY 30 TUESDAY AFTERNOON THEN STRENGTHENING TO NORTHEASTERLY GALES 35 TUES- DAY EVENING, MOSTLY CLOUDY WITH SNOW. FOG AND MIST PATCHES. VISIBILITY FAIR IN SNOW, FAIR IN MIST AND POOR IN FOG. OUTLOOK FOR WEDNESDAY GALE FORCE NORTHEASTERLIES BECOMING GALE'- FORCE NORTHER-</Title>
  <Section position="3" start_page="0" end_page="563" type="intro">
    <SectionTitle>
1. Natural Language Report Synthesis
</SectionTitle>
    <Paragraph position="0"> We use the term &amp;quot;natural language report synthesis&amp;quot; (NLRS) to describe the process of creating well-formed text which summarizes formatted data in a given domain using a style which mirrors the conventions of professional report writers for that domain.</Paragraph>
    <Paragraph position="1"> NLRS for highly reslricted domains was first demonstrated in the work of Kukicb_ (1983) on &amp;quot;knowledge-based generation&amp;quot; of stock market reports. Kukich's ANA system produces professionalsounding stock market stmlmaries using a daily trace of Dow Jones' half-hourly quoudions for the market average and major indices.</Paragraph>
    <Paragraph position="2"> Both ANA and the analogous FRANA system for French (Contant 1986) have used a phrasal lexicon approach (Beeker 1975) which limits the generality of the linguistic component, but which seems to suffice for small and stereotyped domains. The work described below represents a more modular approach to NLRS as well as a new application domain.</Paragraph>
    <Paragraph position="3"> 2. Synthesis of Arctic Marine Weather Forecasts The RAREAS system was developed during a five-month effort to explore the feasibility of synthesizing marine weather bulletins from formatted weather forecast data. The particular task was to produce Arctic marine forecasts for five forecast areas to the east of Baffin Island (known as FPCN25 forecasts). Marine forecasts are one of several types of weather bulletin based on the same basic weather data, each type emphasizing the conditions of interest to a particular corurrmnity of users. In the case of marine bulletins, linguistic emphasis is placed on wind direction and speed, dangerous wind and freezing spray conditions, etc. RAREAS is designed to be sufficiently modular and flexible so as to allow easy extension and adaptation to other types of weather bulletin (e.g., agricultural bulletins, public weather forecasts). Although the current project seems to have proved the feasibility of automatically synthesizing weather forecasts, extensive testing and refinement is required before RAREAS or any successor can be introduced into daily use.</Paragraph>
    <Paragraph position="4"> The RAREAS system is the natural language component of the MARWORDS project, which envisages automating the process of creating bulletins from meteorological information. In the current manual procedure all the available meteorological information (observations, radar and satellite imagery, and numerical weather prediction products) is made available to the weather forecaster. The weather forecaster must correctly diagnose the meteorological processes which will affect his particular area of interest throughout the forecast period, and then translate this knowledge into appropriate textual forecasts for various users.</Paragraph>
    <Paragraph position="5"> In the proposed automated process, MARWORDS will use predicted values for meteorological parameters such as wind speed and direction, cloud cover, and others. In some cases, these predictions could be obtained directly from numerical weather prediction products. In most cases though, they would still be the result of a manual (i.e., human) forecasting procedure. MARWORDS will significantly reduce the workload on the forecaster, making it possible to focus more attention on meteorological problems.</Paragraph>
    <Paragraph position="6"> In the normal course of events, the predicted values make up a continuum in both time and space. For simplicity, values are often given at regular steps in time (e.g., hourly) and space (either at grid points, or at weather observing sites). Alternatively, forecast parameters may be given in terms of significant changes only. MARWORDS is flexible enough to accept both types of data description.</Paragraph>
    <Paragraph position="7"> In fact, the structure and nature of the required data is a problem which needs more work to resolw~.</Paragraph>
    <Paragraph position="8"> 3. Design of the RAREAS system A major task in designing RAREAS was the definition of an input data format which properly divides the work between the MARWORDS expert system, which computes predicted values of weather parameters based on large-scale observations, and RAREAS itself, which interprets that data under local conditions for the purpose of marine forecasts. The format and its permissible content should be sufficiently rich in expressive power to reflect the nuances found in natural language forecasts. Ideally, the expert system should be kept as independent of forecast purpose as possible. RAREAS should therefore take care of all matters related to subjective evaluation of the data (e.g., importance of individual parameters of marine forecasts), as well as the linguistic expression of data values and data relations.</Paragraph>
    <Paragraph position="9"> In its current implementation RAREAS reads the formatted forecast data and carries out (sequentially) the following major operations: null  - reading and parsing of formatted input data, with the interpretation of certain coded values; - checking of data for consistency and plausibility, using data-bases of geographical and meteorological information; - insertion of default values when needed; - detection of conditions which are hazardous for marine operalions (e.g., freezing spray, calculated as a function of forecast wind speed and air temperature, and of a seasonally and regionally adjusted water temperature taken from the database); - &amp;quot;merging of areas&amp;quot;, namely, a check for similarity in the data  for contiguous forecast areas; when similarity threshold conditions are satisfied a single report formula is created for the merged areas under a header which lists those areas;  - suppression of data not sufficiently salient for explicit inclusion in the report (e.g., temperature is generally dropped after its use to check if freezing spray conditions are present); - synthesis of pre-linguistie (&amp;quot;logical&amp;quot;) representation for each sequence of weather events; - interpretation of transitions between weather events into same pre-linguistic form; - segmentation of logical structures into more.independent pre-linguistic clauses and sentences; - mapping of clausal form into English word strings, using  proper terminology and style.</Paragraph>
    <Paragraph position="10"> These diverse functions are carried out by relatively independent modules written in MProlog.</Paragraph>
  </Section>
class="xml-element"></Paper>