<?xml version="1.0" standalone="yes"?>
<Paper uid="E91-1039">
  <Title>AUTOMATIC SEMANTIC CLASSIFICATION OF VERBS FROM THEIR SYNTACTIC CONTEXTS: AN IMPLEMENTED CLASSIFIER FOR STATIVITY</Title>
  <Section position="6" start_page="0" end_page="0" type="concl">
    <SectionTitle>
3 Conclusions
</SectionTitle>
    <Paragraph position="0"> This work demonstrates a promising approach to automatic semantic classification of verbs based only on their immediate linguistic contexts. Some sort of statistical smoothing is essential to avoid being permanently mislead by anomalous and misunderstood utterances, and this work demonstrated the sufficiency of an-approach based on binomial confidence-intervals. These methods, in combination with pure collocational methods like those of \[Hindle, 1990\] and \[Smadja and McKeown, 1990\], may eventually yield substantial progress toward automatic acquisition of word meaning, or some aspects thereof, by language using devices.</Paragraph>
    <Paragraph position="1"> The initial results described here suggest many more experiments, some of which are already u~nderway (see Brent and Berwick, 1991).</Paragraph>
    <Paragraph position="2"> These include attempting to take into account the ability of local syntactic context to influence a verb's meaning as well as to reveal it. For example, think that is stative while think about and think of are not. Separating these two senses automatically could add substantial power to our classifier. Next, there are many more linguistic cues to verb meaning to be detected and exploited. For example, the ability to take both adirect object and a propositional complement, as in &amp;quot;tell him that he's a fool&amp;quot;, reveal verbs of communication. While the progressive cue is not available in Romance languages, the ability to take a direct object and a propositional complement seems to be diagnostic of communication verbs in Romance as well as in English. It would be valuable to demonstrate cues like this on non-English text. It would also be valuable to apply these techniques to a greater variety of input sentences, including transcriptions of mother's speech to their children. Finally, substantially larger corpora should be used in order to enlarge the number of verbs classified. All of these planned extensions serve the goal of automatically classifying thousands of verbs by dozens of different syntactic criteria, and thereby yielding a valuable, adaptable lexicon for natural language processing and artificial intelligence.</Paragraph>
  </Section>
class="xml-element"></Paper>