<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1161">
  <Title>Acquisition of Semantic Classes for Adjectives from Distributional Evidence</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Classification and Hypothesis
</SectionTitle>
    <Paragraph position="0"> As mentioned above, the semantic classification of adjectives is not settled in theoretical linguistics.</Paragraph>
    <Paragraph position="1"> Much research in formal semantics has focused on relatively minor classes (see Hamann (1991) for an overview), which causes coverage problems for NLP systems. Standard descriptive grammars do propose broad-coverage classifications (see Picallo (2002) for Catalan), but these usually mix morphological, syntactic and semantic criteria. We therefore turned to classifications tailored for NLP systems, and defined two parameters largely inspired by Raskin and Nirenburg (1995): a0 unary or binary adjectives, according to whether they have one or two arguments.</Paragraph>
    <Paragraph position="2"> a0 basic, object or event adjectives, according to whether they denote non-decomposable properties, or it can be postulated that they have an object or event component in their meaning.</Paragraph>
    <Paragraph position="3"> This classification was originally devised for systems using an external ontology (so that semantic representations are directly linked to concepts in the ontology), but it is also suitable for broader settings, as we argue in the rest of the Section. We now turn to briefly present the syntax of adjectives in Catalan and discuss the parameters in more detail.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
2.1 Syntax
</SectionTitle>
      <Paragraph position="0"> The default function of the adjective in Catalan is that of modifying a noun; the default position is the postnominal one (about 66% of adjective tokens in the corpus used for the experiments modify nouns postnominally). However, some adjectives can appear prenominally, mainly when used non-restrictively (so-called &amp;quot;epithets&amp;quot;; 26% of the tokens occur in prenominal position).</Paragraph>
      <Paragraph position="1"> The other main function of the adjective is that of predicate in a copular sentence (6% of the tokens).</Paragraph>
      <Paragraph position="2"> Other predicative contexts, such as adjunct predicates, are much less frequent (approx. 1% of the adjectives in the corpus).</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
2.2 Unary vs. binary
</SectionTitle>
      <Paragraph position="0"> Unary adjectives have only one argument, usually corresponding to the modified noun (a red balla1a3a2a5a4a7a6 ) or the subject in a copular sentence (this balla1a3a2a8a4a7a6 is red). Binary adjectives have two arguments, one analogous to ARG1 and another one which usually corresponds to a PP complement (a teachera1a3a2a8a4a7a6 jealous of Marya1a8a2a8a4a3a9 , this teachera1a3a2a5a4a7a6 is jealous of Marya1a8a2a8a4a3a9 ). Thus, unary adjectives denote properties and binary adjectives denote relations.</Paragraph>
      <Paragraph position="1"> From a linguistic point of view, we expect binary adjectives to co-occur with postponed prepositions with a significant higher frequency than unary ones.</Paragraph>
      <Paragraph position="2"> Similarly, because of the heaviness of the PP, we expect them to frequently occur in predicative constructions, that is, after a verb.</Paragraph>
      <Paragraph position="3"> The arity is a basic parameter for the semantic characterisation of any predicate. It is useful for low-level tasks such as parsing (e.g. for PP-attachment ambiguity within NPs), but also for tasks oriented to semantics, such as the extraction of relationships between individuals or concepts.</Paragraph>
      <Paragraph position="4"> 2.3 Basic denotation vs. object component vs.</Paragraph>
      <Paragraph position="5"> event component Basic adjectives denote attributes or properties which cannot be decomposed; for instance, red or jealous. Adjectives which have an event component in their meaning (event adjectives for short) denote a state that is directly dependent on an event, be it simultaneous or previous to the state. Examples would be directed, flipping or constitutive. Similarly, object adjectives have an embedded object component in their meaning: pulmonary disease can be paraphrased as disease that affects the lungs, so that pulmonary evokes the object lungs. Other examples would be economic or agricultural.1 We expect object adjectives to have a rigid position, right after a noun (in Catalan). Any other modifiers or complements (PPs, other adjectives, etc.) will occur after the object adjective. This restriction also implies that they will have very low frequencies for predicative positions.</Paragraph>
      <Paragraph position="6"> Event adjectives, on the contrary, appear most naturally in predicative environments. This is probably due to the fact that most of them are deverbal and thus inherit part of the verbal argument structure. Thus, they tend to form larger constituents that are mostly placed in predicative position. For the same reason, they will appear in postnominal position when acting as modifiers.</Paragraph>
      <Paragraph position="7"> As for basic adjectives, most of them can be used nonrestrictively, so that they will appear both postnominally and prenominally. In addition, there is no restriction keeping them from appearing in predicative constructions. When combined with other kinds of adjectives, mainly object adjectives, they will appear at the peripheria (an`alisi pol'itica seriosa, 'serious political analysis').</Paragraph>
      <Paragraph position="8"> This parameter can again be used for basic tasks such as POS-tagging: Adjective-noun ambiguity is notoriously the most difficult one to solve, and the ordering restrictions on the classes of adjectives can help to reduce it. However, it is most useful for semantic tasks. For instance, object adjectives can evoke arguments when combined with predicative nouns (presidential visit - a president visits X). For projects such as FrameNet (Baker et al., 1998), 1Note that we do not state that adjectives denote objects or events, but that they imply an object or event in their denotation. This kind of adjectives denotes properties or states, but with an embedded or &amp;quot;shadow&amp;quot; argument (Pustejovsky, 1995), similarly to verbs like to butter.</Paragraph>
      <Paragraph position="9"> these kinds of relationships could be automatically extracted if information on the class were available.</Paragraph>
      <Paragraph position="10"> The same applies to event adjectives, this time being predicates (flipping coin - a coin flips).</Paragraph>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
2.4 Morphology vs. syntax
</SectionTitle>
      <Paragraph position="0"> It could seem that the semantic classes established for the second parameter amount to morphological classes: not derived (basic adjectives), denominal (object adjectives), and deverbal (event adjectives).</Paragraph>
      <Paragraph position="1"> However, although there is indeed a certain correlation between morphological class and semantic class, we claim that morphology is not sufficient for a reliable classification because it is by no means a one-to-one relationship.</Paragraph>
      <Paragraph position="2"> There are denominal adjectives which are basic, depending on the suffix (e.g. -'os as in vergony'os, 'shy') and on whether they have developed a different meaning than the etymological one, such as marginal, 'marginal', which has come to be used as synonymous to 'rare, outsider-like'. Conversely, some object adjectives are not synchronically denominal, such as bot`anic, 'botanical'. The same happens with event as opposed to deverbal adjectives: a deverbal adjective such as amable (lit. 'suitable to be loved', has derived to 'kind, friendly') has now a basic meaning (we have not found any non-deverbal adjective to have an event-type denotation). null Our hypothesis, which will be tested on Section 4.3, is that syntax is more reliable than morphology as a basis for semantic classification. The intuition behind this hypothesis is that if a certain suffix forms basic adjectives, they will behave like ordinary basic adjectives; similarly, if a derived adjective has undergone semantic change and as a result has shifted class, it will also behave like an ordinary adjective of the target class.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>