<?xml version="1.0" standalone="yes"?>
<Paper uid="P97-1071">
  <Title>Contrastive accent in a data-to-speech system</Title>
  <Section position="5" start_page="519" end_page="520" type="metho">
    <SectionTitle>
3 An alternative solution
</SectionTitle>
    <Paragraph position="0"> Fortunately, in data-to-speech systems like GoalGetter, the input of which is formed by typed and structured data, a simple principle can be used for determining contrast. If two subsequent sentences are generated from the same type of data structure they express similar information and should therefore be regarded as potentially contrastive, even if their surface forms are different. Pitch accent should be assigned to those parts of the second sentence that express data which differ from those in the data structure expressed by the first sentence.</Paragraph>
    <Paragraph position="1"> Example (1) can be used as illustration. The theory of Prevost will not predict contrastive accent on Ajax in (1)b, because (1)a does not contain a member of its alternative set. In Pulman's approach, the contrast can only be predicted if the system uses the world knowledge that scoring an own goal means scoring for the opposing team. In the approach that I propose, the contrast between (1)a and b can be derived directly from the data structures they express.</Paragraph>
    <Paragraph position="2"> Figure 1 shows these structures, A and B, which are both of the type goaLevent: a record with fields specifying the team for which a goal was scored, the player who scored, the time and the kind of goal: normal, own goal or penalty.</Paragraph>
    <Paragraph position="3">  Since A and B are of the same type, the values of their fields can be compared, showing which pieces of information are contrastive. Figure 1 shows that all the fields of B have different values from those of A. This means that each phrase in (1)b which expresses the value of one of those fields should receive contrastive accent, 2 even if the corresponding field value of A was not mentioned in (1)a. This guarantees that in (1)b the proper name Ajax, which expresses the value of the team field of B, is accented despite the fact that the contrasting team was not explicitly mentioned in (1)a.</Paragraph>
    <Paragraph position="4"> The discussion of example (1) shows that in the approach proposed here no world knowledge is needed to determine contrast; it is only necessary to compare the data structures that are expressed by the generated sentences. The fact that the input data structures of the system are organized in such a way that identical data types express semantically parallel information allows us to make use of the world (or domain) knowledge incorporated in the design of these data structures, without having to separately encode this knowledge. This also means  that the prediction of contrast does not depend on the linguistic expressions which are chosen to express the input data; the data can be expressed in an indirect way, as in (1)a, without influencing the prediction of contrast.</Paragraph>
    <Paragraph position="5"> The approach sketched above will also give the desired result for example (2): sentence (2)c will not be regarded as contrastive with (2)b, since (2)c expresses a goal event but (2)b does not.</Paragraph>
  </Section>
  <Section position="6" start_page="520" end_page="520" type="metho">
    <SectionTitle>
4 Future directions
</SectionTitle>
    <Paragraph position="0"> An open question which still remains, is at which level data structures should be compared. In other words, how do we deal with sub- and supertypes? For example, apart from the goal_event data type the GoalGetter system also has a card_event type, which specifies at what time which player received a card of which color. Since goal_event and card_event are different types, they are not expected to be contrastible. However, both are subtypes of a more general event type, and if regarded at this higher event level, the structures might be considered as contrastible after all. Examples like (3) seem to suggest that this is possible.</Paragraph>
    <Paragraph position="1"> (3) a In the 11th minute, Ajax took the lead through a goal by Kluivert.</Paragraph>
    <Paragraph position="2"> b Shortly after the break, the referee handed Nilis a yellow card.</Paragraph>
    <Paragraph position="3"> c Ten minutes later, Kluivert scored for the second time.</Paragraph>
    <Paragraph position="4"> The fact that it is not inappropriate to accent Kluivert in (3)c, shows that (3)c may be regarded as contrastive to (3)b; otherwise, it would be obligatory to deaccent the second mention of Kluivert due to givenness, like PSV in (2)c. Cases like this might be accounted for by assuming that there can be contrast between fields that are shared by data types having the same supertype. In (3), these would be the player and the minute fields of structures C and D, shown in Figure 2. This is a tentative solution which requires further research.</Paragraph>
    <Paragraph position="5"> player: Nilis \] C: card_event minute: 11</Paragraph>
  </Section>
class="xml-element"></Paper>