<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2209">
  <Title>Reactive Content Selection in the Generation of Real-time Soccer Commentary</Title>
  <Section position="8" start_page="1284" end_page="1284" type="concl">
    <SectionTitle>
7 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> We have described how MIKE, a live commentary generation system for the game of soccer, deals with the issues of real time content selection and realization. null MIKE uses heterogeneous modules to recognize various low-level and high-level features from basic input information on the positions of the ball and the players. An NL generator then selects contents from a large number of propositions describing these features.</Paragraph>
    <Paragraph position="1"> The selection of contents is controlled by importance scores that intuitively capture the amount of information communicated to the audience. Under our principle of maximizing the total importance scores communicated to the audience, the decision on how a content should be realized considering rearrangements such as interruption, abbreviation, is decided at the same time as the selection of a content. Thus, one of our discoveries was that severe when-to-say restriction works to tightly incorporate what-to-say (content selection) module and a how-to-say (language realization) module.</Paragraph>
    <Paragraph position="2"> We presented sample commentaries produced by MIKE in English, French and Japanese. The effect of using the rearrangements was shown compared and found to increase the total importance scores by 10%, to decrease delay of the commentary by 14%.</Paragraph>
    <Paragraph position="3"> An important goal for future work is parameter learning to allow systematic improvement of MIKE'S performance. Although the parameters used in the system should ideally be extracted from the game log corpus, this opportunity is currently very limited; only the game logs of RoboCup'97 (56 games) and JapanOpen-98 (26 games) is open to public.</Paragraph>
    <Paragraph position="4"> Additionally, no model commentary text corpus is available. One way to surmount the lack of appropriate corpora is to utilize feedback from an actual audience. Evaluations and requests raised by the audience could be automatically reflected in parameters such as the initial values for importance scores, rates of decay of these scores, the coefficients in the formulae used for controlling inferences.</Paragraph>
    <Paragraph position="5"> Another important research topic is the incorporation of more sophisticated natural language generation technologies in MIKE to produce a more lively, diverse output. At the phrase generation level, this includes the generation of temporal expressions, anaphoric references to preceding parts of the commentary, embedded clauses. At the more surface level, these are many research issues related to text-to-speech technology, especially prosody control. null</Paragraph>
  </Section>
class="xml-element"></Paper>