<?xml version="1.0" standalone="yes"?>
<Paper uid="P97-1071">
  <Title>Contrastive accent in a data-to-speech system</Title>
  <Section position="4" start_page="0" end_page="519" type="intro">
    <SectionTitle>
2 Predicting contrastive accent
</SectionTitle>
    <Paragraph position="0"> In this section I discuss two approaches to predicting contrastive accent, which were put forward by Scott Prevost (1995) and Stephen Pulinan (1997).</Paragraph>
    <Paragraph position="1"> In the theory of contrast proposed in (Prevost, 1995), an item receives contrastive accent if it co-occurs with another item that belongs to its 'set of alternatives', i.e. a set of different items of the same type. There are two main problems with this approach. First, as Prevost himself notes, it is very difficult to define exactly which items count as being of 'the same type'. If the definition is too strict, not all cases of contrast will be accounted for. On the other hand, if it is too broad, then anything will be predicted to contrast with anything. A second problem is that there are cases where co-occurrence of two items of the same type does not trigger contrast, as in the following soccer example: (2) a</Paragraph>
    <Paragraph position="3"> After six minutes Nilis scored a goal for PSV.</Paragraph>
    <Paragraph position="4"> This caused Ajax to fall behind.</Paragraph>
    <Paragraph position="5"> Twenty minutes later Cocu scored for PSV.</Paragraph>
    <Paragraph position="6"> According to Prevost's theory, PSVin (2)c should have a contrastive accent, because the two teams Ajax and PSV are obviously in each other's alternative set. In fact, though, there is no contrast and PSV should be normally deaccented due to givenness. This shows that the presence of an alternative item is not sufficient to trigger contrast accent.</Paragraph>
    <Paragraph position="7">  Another approach to contrastive accent is advocated by Pulman (1997), who proposes to use higher order unification (HOU) for both interpretation and prediction of focus. Described informally, Pulman's focus assignment algorithm takes the semantic representation of a sentence which has just been generated, looks in the context for another sentence representation containing parallel items, and abstracts over these items in both representations. If the resulting representations are unifiable, the two sentences stand in a contrast relation and the parallel elements from the most recent one receive a pitch accent (or another focus marker).</Paragraph>
    <Paragraph position="8"> Pulman does not give a full definition of parallelism, but states that &amp;quot;to be parallel, two items need to be at least of the same type and have the same sortal properties&amp;quot; ((Pulman, 1997), p. 90). This is rather similar to Prevost's conditions on alternative sets. Consequently, Pulman's theory also faces the problem of determining when two items are of the same type. Still, contrary to Prevost, Pulman can explain the lack of contrast accent in (2)c, because obviously the representations of sentences (2)b and (2)c will not unify.</Paragraph>
    <Paragraph position="9"> Another advantage, pointed out in (Gardent et al., 1996), is that a HOU algorithm can take world knowledge into account, which is sometimes necessary for determining contrast. For instance, the contrast in (1) is based on the knowledge that kicking the ball into the wrong goal implies scoring a goal for the opposing team. In a HOU approach, the contrast in this example might be predicted by unifying the representation of the second sentence with the entailment of the first. However, such a strategy would require the explicit enumeration of all possible semantic equivalences and entalhnents in the relevant domain, which seems hardly feasible. Also, implementation of higher order unification can be quite inefficient. This means that although theoretically appealing, the HOU approach to contrastive accent is less attractive from a computational viewpoint.</Paragraph>
  </Section>
class="xml-element"></Paper>