<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2247">
  <Title>Detecting Verbal Participation in Diathesis Alternations</Title>
  <Section position="6" start_page="1494" end_page="1494" type="evalu">
    <SectionTitle>
5 Experimental Results
</SectionTitle>
    <Paragraph position="0"> A subcategorization lexicon was produced from 10.8 million words of parsed text from the British National Corpus. In this preliminary work a small sample of 30 verbs were examined.</Paragraph>
    <Paragraph position="1"> These were selected for the range of SCFs that they exhibit. The primary alternation selected was the causative-inchoative because a reasonable number of these verbs (15) take both sub-categorization frames involved. ATCM models were obtained for the data at the subject of the intransitive frame and object of the transitive.</Paragraph>
    <Paragraph position="2"> The cost of these models was then compared to the cost of the model produced when the two data sets were combined.</Paragraph>
    <Paragraph position="3"> Table 1 shows the results for the 15 verbs which took both the necessary frames. The system's decision as to whether the verb participates in the alternation or not was compared to the verdict of a human judge. The accuracy was 87%( 4+9 ~ Random choice would give ~, 4+1+9+1/&amp;quot; a baseline of 50%. The cause for the one false positive cut was that cut takes the middle alternation (The butcher cuts the meat ~-~ the meat cuts easily). This alternation cannot be distinguished from the causative-inchoative because the scF acquisition system drops the adverbial and provides the intransitive classification.</Paragraph>
    <Paragraph position="4"> Performance on the simple reciprocal intransitive alternation (John agreed with Mary Mary and John agreed) was less satisfactory. Three potential candidates were selected by virtue of their SCFs swing;with add;to and agree;with. None of these were identified as taking the alternation which gave rise to 2 true negatives and I false negative. From examining the results it seems that many of the senses found at the intransitive slot of agree e.g. policy would not be capable of alternating. It is at least encouraging that the difference in the cost of the separate and combined models was low.</Paragraph>
  </Section>
class="xml-element"></Paper>