<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2204">
  <Title>Constructing Verb Semantic Classes for French: Methods and Evaluation</Title>
  <Section position="4" start_page="1127" end_page="1129" type="metho">
    <SectionTitle>
3 Construction of verb classes
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="1127" end_page="1128" type="sub_section">
      <SectionTitle>
3.1 Typology of the verb sample
</SectionTitle>
      <Paragraph position="0"> The experiment presented here has been realized on a set of 1700 usual verbs which are the most frequently used in French. Our aim is to classify  3000 to 4000 verbs. The size of the sample considered so far is however sufficiently large to allow us to draw significant and precise conclusions. It should be noticed that contexts are associated with a given word-sense, not wilh all the senses of a verb. Each sense of a polysemous verb is associated with a different set of contexts. The description of a verb is the following: verb(\[verb\],arity, \[basic context number\], \[thematic grid\],\[prepositions\], \[list of contexts\]).</Paragraph>
      <Paragraph position="1"> verb(\[admirer\],3,\[20\],\[ae,tib,src\],\[pour\], \[50,51,61,i02,150,171,180\]).</Paragraph>
      <Paragraph position="2"> (ae = effective agent, tib = incremental beneficiary theme, src = source). Contexts have been associated with verbs on the basis of a nmnber of linguistic analyses of French (e.g. (Gross 75)), of already existing lexicons, and from corpora inspection and our own intuitions.</Paragraph>
    </Section>
    <Section position="2" start_page="1128" end_page="1128" type="sub_section">
      <SectionTitle>
3.2 A simple verb classification
</SectionTitle>
      <Paragraph position="0"> We have carried out a simple classitication where a verb class contains all the verbs which accept exactly the same set of contexts. This is not the classification method adopted by Beth Levin: her verb classes are constructed from subsets of alternations, intuitively selected, which are sufficiently selective to allow for the characterization of a set of semantically related verbs. Exceptions are allowed in order to elt&gt;ctively gather all the verbs which are intuitively semantically related. Her classification method, based on a large number of linguistic analyses involving some subtle semantic criteria (e.g. intentionality), can only be carried out manually and is therefore not adapted to our approach.</Paragraph>
      <Paragraph position="1"> We obtain a total of 953 classes. We get a large number of classes with just one element (about 77%), this is not surprising, however, since contexts can be combined in a large number of ways.</Paragraph>
      <Paragraph position="2"> 56% of the verbs appear in classes with at least 2 elements, and 33% of them are in classes with at least 5 elements.</Paragraph>
      <Paragraph position="3"> This number of classes is quite large compared to Beth Levin's results (about 200 classes), however, our classes have been constructed on a strict equivalence class basis, without any exceptions, and all the contexts have been taken into account.</Paragraph>
      <Paragraph position="4"> We have an average of 1.8 verbs per class. A similar result was also obtain by (Gross 75), on a difi'erent basis (including morphology) and with more criteria (about 200).</Paragraph>
      <Paragraph position="5"> A very informal study of the progression of the number of classes tends to indicate that the increase of the number of new classes is not linear, but progressively decreases. It seems that beyond 2500 verbs almost no new verb class should be created, defining about 1100 to 1200 classes. But this is clearly too much.</Paragraph>
    </Section>
    <Section position="3" start_page="1128" end_page="1129" type="sub_section">
      <SectionTitle>
3.3 Evaluation of the semantic
</SectionTitle>
      <Paragraph position="0"> relatedness of verb gemantic classes The overall quality of the verb classes are studied in detail in (Saint-Dizier 95). With the same set of verb-senses, we have carried out a classification similar to the classification proposed in WordNet. Besides the main categories presented in (Fe\]lbaum 93), we have added two classes: aspectual verbs and verbs expressing causality. We have then subdivided these main categories according to different types of properties or constraints following as much as possible those defined in WordNet. In our current classification, we consider 198 hierarchically organized classification criteria, instances of the is-a (or troponymy) relation, the depth of the decomposition is 3 (Saint-Dizier 96). We therefore get 198 verb classes (called WN classes) for levels 1 to 3. For example, a three level decomposition is for raovemcn! verbs (level 1), directed motion, local motion, etc.</Paragraph>
      <Paragraph position="1"> (level 2) and upward motion, downward motion, etc. (level 3).</Paragraph>
      <Paragraph position="2"> If we now compare the degree of overlapp between the classes (with at least 2 elements) formed above from syntactic contexts (called VS classes) and those of WN, we get the following results:  a WN class at this level.</Paragraph>
      <Paragraph position="3"> Classes where verbs are associated with at least 5 contexts are of a much better quality (semantic relateuess with WN classes above 64%) than those under 5. The best classes contain an average of 4 to 7 verbs, larger classes (above 10 elements) are often of a lower quality or may contain several subsets of semantically related verbs: in a large number of classes with more than 8 elements we tbund 2 or 3 subsets of classes of WN.</Paragraph>
      <Paragraph position="4"> These classes are often formed from a small nmnbet of contexts (1 to 3), which explains their low semantic relatedness rate.</Paragraph>
      <Paragraph position="5"> Globally, these results aren't very good. If we want to explore in more depth the cooperation between syntax and semantics, and if we want to be able to construct verb semantic classes on a rigourous basis, it is necessary to develop methods that improve the quality of VS classes (considering that syntactic criteria are the most 'rigourous' ones a priori). The first approach, which is the simplest, is to make the classification more flexible by allowing exceptions: a verb in a class may have one more or one less context than the norm of the class. This approach gives however very bad results, with an overlapp VS/WN rate below 35%.</Paragraph>
      <Paragraph position="6"> To improve that rate, exceptions should depend  on the VS class, but this is extremely subjective and hard to carry out. The second type of solution consists in analyzing the implicit semantics conveyed by contexts and to form classes from sets of contexts, on the basis of their implicit semantics.</Paragraph>
      <Paragraph position="7"> Then all the verbs accepting exactly an a priori given set of contexts will belong to the same VS class, even if they accept many other contexts.</Paragraph>
    </Section>
  </Section>
  <Section position="5" start_page="1129" end_page="1129" type="metho">
    <SectionTitle>
4 Analysis of the semantics
</SectionTitle>
    <Paragraph position="0"> conveyed by contexts Some contexts are quite general and are not related to precise semantic notions, while others convey clearly identifiable meaning components. First, there are contexts which convey very precise meaning components, which are not taken into account, for various reasons, in WordNet classifications. For example, the context of the form 'pousser + nominalization of verb' is associated with verbs of sound emission: painful sounds for humans and any sound for animals; verbs which accept the 'dans/en-de preposition change' convey an idea of putting something into something else ( bourrer le tuyau de papicr, bourrer le papier daus le tuyau).</Paragraph>
    <Paragraph position="1"> Next, a second type of context conveys meaning components which can directly be associated with WN criteria. We have carried out a detailed analysis of the correlations between WN criteria and contexts. There are 19 non-basic contexts (out of 47), which can very clearly be associated with 1 or 2 WN criteria. For example, context 91, (je fats atterir l'avion ('I make land the plane')), is at 90% associated with verbs of body care. Context 151, (alternation 2.13.4 in Beth Levin: Les grimaces de Jean terrifient Sophie), is associated at a rate of 60% with psychological verbs. This is studied in detail in (Saint-Dizier 96).</Paragraph>
  </Section>
class="xml-element"></Paper>