<?xml version="1.0" standalone="yes"?>
<Paper uid="E89-1015">
  <Title>FOCUS AND ACCENT IN A DUTCH TEXT.TO-SPEECH SYSTEM</Title>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
VERWOEST
</SectionTitle>
    <Paragraph position="0"> in Zeist is a factory by fire destroyed The following condition is proposed in order to account for this type of data:</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4. Assigning focus
</SectionTitle>
    <Paragraph position="0"> Assnrnln~ that a programme for semantic interpretation of unrestricted Dutch text will not be available within the near future, the following practical strategy is proposed for assic, ning focus to constituents in a syntactic tree. This strategy is based on the insight that word classes differ with respect to the amount of information that is typically conveyed by their members. The central idea is to assign  \[+focus\] to the maximal projections of categories that convey extra-grammatical meaning (nouns, adjectives, vex'bs, numerals and most of the adverbs). In addition, \[-focus\] is assigned to pronouns. In the case of a coordination, \[ +focus\] is assigned to each conjunct. Finally, \[ +focus\] is assigned to the sisters of focus-governing elements like niet 'not', ook 'also', alleen 'only', ze~fs 'even', etc. Below I informally present an accent assignment algorithm which combines these focus assignment heuristics with the focus-to-accent rules discussed in section 3:  (1) Read a sentence with its surface structure representation.</Paragraph>
    <Paragraph position="1"> (2) Assign the labels w and s to nodes in the tree, according to the BLR above.</Paragraph>
    <Paragraph position="2"> (3) Assign \[-focus\] to pronouns.</Paragraph>
    <Paragraph position="3"> (4) Apply DA: if an s-node is \[-focus\], replace s by w for this node and w by s for its sister.</Paragraph>
    <Paragraph position="4"> (5) Apply the RR, starting out from the most deeply embedded subtrees.</Paragraph>
    <Paragraph position="5"> (6) Assign \[+focus\] to S, (non-pronomlnal) NP, AP, AdvP and NumP nodes.</Paragraph>
    <Paragraph position="6"> (7) Assign \[+focus\] to each member of a coordination.</Paragraph>
    <Paragraph position="7"> (8) Assign \[+focus\] to the sister of a focus governor.</Paragraph>
    <Paragraph position="8"> (9) Assign \[+focus\] to every s-node, the  sister of which has been assigned \[ + focus\] (thus avoiding prosodic mismatch, see the PMC above).</Paragraph>
    <Paragraph position="9"> (10) Assign accent to each word that is connected to a dominating \[+focus\] node via a path that consists exclusively of snodes. null  (11) Stop.</Paragraph>
    <Paragraph position="10"> 5. Perceptual evaluation  The accent assi~ment algorithm has been implemented as a Pascal programme. Input to this programme is a Dutch sentence; the user is asked to provide information about syntactic bracketing and labelling, and about the argument status of constituents. The programme next assigns focus structure and w/s labelling to the sentence and outputs the predicted accent pattern.</Paragraph>
    <Paragraph position="11"> A small informative text was used for evaluation of the output of the programme. In this evaluation experiment, the predicted accent patterns were compared with the accent patterns spontaneously produced by a human reader, as well as with the accent patterns as predicted by a naive accentuation algorithm which assigns an accent to every content word. Listeners were asked to rate the quality of sentences synthesized with the respective accent patterns on a 7-point scale. As a snmmary of the results, I here present the mean scores for each of the conditions: Spontaneous accentuatiom 5.2 Sophisticated algorithm: 4.6 Naive algorithm&amp;quot; 3.3 As one can see, human accentuation is stili preferred over the output of the algorithm of section 4. Of course this is what we expect, as the algorithm does not have access to the semantico-pragmatic properties of an input text, such as coreferenco and contrast. On the other hand we see that the algorithm, which does take syntactic effects on accent placement into account, offers a substantial improvement over a simple algorithm based on the content word - function word distinction.</Paragraph>
  </Section>
class="xml-element"></Paper>