<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0805">
  <Title>Lexical Discrimination with the Italian Version of WORDNET</Title>
  <Section position="7" start_page="35" end_page="36" type="evalu">
    <SectionTitle>
5 Experiments and Results
</SectionTitle>
    <Paragraph position="0"> In this section we describe the empirical results obtained by coupling a WoRDNET based lexicon with a parser In our intention, the experiment would bring evidence for the following aspects: . Plausibility of WoRDNBT senses for describing a lexical entries; e Usability of WoRDNET for carrying out lexical discrimination. null The experiment has been carried out on 60 sentences with 1201 different lectures, and formed by using seven verbs (wr~te, eat, smell, corrode, buy, receive, assocza~e) coupled with fifty common nouns and two proper nouns. In the general experimental setting a sentence is given to the parser in a situation characterized by multiple lexical entries for each single word (one for each WoRDNET sense). The analyses produced by the parser are compared with the set of interpretations given by a human. As far as nouns are concerned, a lexlcal entry includes all the senses found in Italian WORDNET. Some of the nouns used in the experiment are shown in figure 5. As for verbs, we started from the Italian WoRDNET senses and then we faced to the problem of mdividuatmg the proper selectional restrictions for each argumental position of the verb subcategorization frame as seen before. So we build a small number of lexical entries, by means of which we composed the sentences of the experiment.</Paragraph>
    <Paragraph position="1"> We experiment the two hypotheses on selectional restrictions presented in section 3, i.e., the one with general WoRDNET frames and the other with more refined selectional restrictions.</Paragraph>
    <Paragraph position="2"> As an example, figure 6 shows the output of the parser for the sentence &amp;quot;La regzna scrtsse ~ma leltera a Gzovanng' (&amp;quot;The queen wrote a letter to John&amp;quot;). As a convenction, we decided to describe internal arguments with the symbol '/', while a '//' denotes a verbal adjunct.</Paragraph>
    <Paragraph position="3"> This sentence was selected because it produces an high number of lectures (40) among the test suite sentences.</Paragraph>
    <Paragraph position="4"> This is due to both the verb sense ambiguity (write has five senses) and to the noun ambiguitms (queen has five senses, and letter two). Note that the parser excludes the sense Write-Publish since the indirect object must be introduced by the Italian prepositions &amp;quot;su&amp;quot; or &amp;quot;per ~' (in English &amp;quot;on&amp;quot; or &amp;quot;fort'), while in this example we have the preposition &amp;quot;a&amp;quot; (&amp;quot;to&amp;quot;).</Paragraph>
    <Paragraph position="5"> Let us first consider the results obtained in the second experimental setting, which best approximate the human judgment. Out of the eight interpretations accepted, two are implausible for a human reader. This caused by the contemporary presence of the sense Letter-Missive and of the proper noun John as, respectively, patient and beneficiary of the write verb sense. Note that, each of these senses are, per se, valid arguments since they satisfy the selectional restrictions.</Paragraph>
    <Paragraph position="6"> In the first experimental setting, the presence of weaker selectional restrictions (just ~omebody, Somethzng) ymlds more spurious readings. As a matter of fact, the more evzdent problem is that many times argumental positions are not properly filled. For example, that &amp;quot;a queen-Regnant could ~/rlte-Music an Letter-Missive&amp;quot; (i.e., a kind of correspondence) is one  periment. They are preliminary since they have been obtained on a limited number of sentences (60). The figure shows, for each experimental setting, the number of total readings produced by the parser, the discrlmination rate (i.e., the rate of the lectures rejected: (1201- z)/1201), and the precision (i.e., the rate of correct lectures: 122/z). These results have to be interpreted considering that the focus of the experiment is on selectional restrictions, which of course is just one among the various kinds of information occurring during lexical discrimination. It is worth mentioning here, among the others, some crucial information sources: (i)  world knowledge: e.g., it is very strange to Write an Article-Clause on a Newspaper-Periodic; (ii) aspectual properties of the verb: e.g., it is very difficult to interpret La regina sta scmvendo un artscolo sul gzonale (The queen ss wmtmg an article on the newspaper) with the Write-Publish sense, because publishing is a culminative process.</Paragraph>
  </Section>
class="xml-element"></Paper>