<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1105">
  <Title>Japanese Dependency Parsing Using Co-occurrence Information and a Combination of Case Elements</Title>
  <Section position="4" start_page="833" end_page="833" type="metho">
    <SectionTitle>
2 Parsing Japanese
</SectionTitle>
    <Paragraph position="0"> The Japanese language is basically an SOV language, but word order is relatively free. In English the syntactic function of each word is represented by word order, while in Japanese it is represented by postpositions. For example, one or more post-positions following a noun play a role similar to the declension of nouns in German, which indicates grammatical case.</Paragraph>
    <Paragraph position="1"> The syntax of a Japanese sentence is analyzed by using segments, called bunsetsu, that usually contain one or more content words like a noun, verb, or adjective, and zero or more function words like a particle (case marker) or verb/noun suffix. By defining a bunsetsu in this manner, we cananalyzeasentenceinawaysimilartothatused when analyzing the grammatical roles of words in inflected languages like German.</Paragraph>
    <Paragraph position="2"> Japanese dependencies have the following characteristics: null * Each bunsetsu except the rightmost one has only one head.</Paragraph>
    <Paragraph position="3"> * Each head bunsetsu is always placed to the right of (i.e. after) its modifier.</Paragraph>
    <Paragraph position="4"> * Dependencies do not cross one another.</Paragraph>
    <Paragraph position="5"> Statistical Japanese dependency analyzers (Kudo and Matsumoto, 2005; Kudo and Matsumoto, 2002; Sassano, 2004; Uchimoto et al., 1999; Uchimoto et al., 2000) automatically learn the likelihood of dependencies from a tagged corpus and calculate the best dependencies for an input sentence. These likelihoods are learned by considering the features of bunsetsus such as their character strings, parts of speech, and inflection types, as well as information between bunsetsus such as punctuation and the distance between bunsetsus. The weight of given features is learned from a training corpus by calculating the weights from the frequencies of the features in the training data.</Paragraph>
  </Section>
  <Section position="5" start_page="833" end_page="834" type="metho">
    <SectionTitle>
3 Japanese dependency analysis taking
</SectionTitle>
    <Paragraph position="0"> account of co-occurrence information and a combination of multiple cases One constraint in Japanese is that multiple nouns of the same case do not modify a verb. Previous work on Japanese dependency analysis has assumed that all the dependency relations are independent of one another. It is therefore necessary to also consider such a constraint as a feature for contextual information. Uchimoto et al., for example, used as such a feature whether a particular type of bunsetsu is between two bunsetsus in a dependency relation (Uchimoto et al., 1999), and Sassano used information about what is just before and after the modifying bunsetsu and modifyee bunsetsu (Sassano, 2004).</Paragraph>
    <Paragraph position="1"> In the artificial example shown in Figure 1, it is natural to consider that &amp;quot;keisatsu-de&amp;quot; will modify &amp;quot;hogo-shita&amp;quot;. Statistical Japanese dependency analyzers (Uchimoto et al., 2000; Kudo and Matsumoto, 2002), however, will output the result where &amp;quot;keisatsu-de&amp;quot; modifies &amp;quot;arui-teiru&amp;quot;. This is because in sentences without internal punctuation a noun tends to modify the nearest verb, and these analyzers do not take into account a combination of multiple cases.</Paragraph>
    <Paragraph position="2"> Another kind of information useful in dependency analysis is the co-occurrence of a noun and a verb, which indicates to what degree the noun tends to modify the verb. In the above example, the possible modifyees of &amp;quot;keisatsu-de&amp;quot; are &amp;quot;arui-teiru&amp;quot; and &amp;quot;hogo-shita&amp;quot;. Taking into account information about the co-occurrence of &amp;quot;keisatsu-de&amp;quot; and &amp;quot;arui-teiru&amp;quot; and of &amp;quot;keisatsu-de&amp;quot; and &amp;quot;hogo-shita&amp;quot; makes it obvious that &amp;quot;keisatsu-de&amp;quot; is more likely to modify &amp;quot;hogo-shita&amp;quot;.</Paragraph>
    <Paragraph position="3">  In summary, we think that statistical Japanese dependency analysis needs to take into account at least two more kinds of information: the dependency relation between multiple cases where multiple nouns of the same case do not modify a verb, and the co-occurrence of nouns and verbs.</Paragraph>
    <Paragraph position="4"> One way to use such information in statistical dependency analysis is to directly use it as features.</Paragraph>
    <Paragraph position="5"> However, Kehler et al. pointed out that this does not make the analysis more accurate (Kehler et al., 2004). This paper therefore presents a model that uses the co-occurrence information separately and reranks the analysis candidates generated by the existing machine learning model.</Paragraph>
  </Section>
  <Section position="6" start_page="834" end_page="835" type="metho">
    <SectionTitle>
4 Our proposed model
</SectionTitle>
    <Paragraph position="0"> We first introduce the notation for the explanation of the dependency structure T: m(T) : the number of verbs in T vi(T) : the i-th verb in T ci(T) : the number of case elements that modify the i-th verb in T esi(T) : the set of case elements that modify the i-th verb in T rsi(T) : the set of particles in the set of case elements that modify the i-th verb in T nsi(T) : the set of nouns in the set of case elements that modify the i-th verb in T ri,j(T) : the j-th particle that modifies the i-th verb in T ni,j(T) : thej-thnounthatmodifiesthei-thverb in T We defined case element as a pair of a noun and following particles. For the dependency structure we assume the conditional probability P(esi(T)|vi(T)) that the set of case elements esi(T) depends on the vi(T), and assume the set of case elements esi(T) is composed of the set of noun nsi(T) and particles rsi(T).</Paragraph>
    <Paragraph position="2"> In the transformation from Equation (2) to Equation (3), we assume that the set of noun nsi(T) is independent of the verb vi(T). And in the transformation from Equation (3) to Equation (4), we assume that the noun ni,j(T) is dependent on only its following particle ri,j(T).</Paragraph>
    <Paragraph position="3"> Now we assume the dependency structure T of  thewholesentenceiscomposedofonlythedependency relation between case elements and verbs, and propose the sentence probability defined by Equation (5).</Paragraph>
    <Paragraph position="5"> We call P(rsi(T)|vi(T)) the co-occurrence probability of the particle set and the verb, and we call P(ni,j(T)|ri,j(T),vi(T)) the co-occurrence probability of the case element set and the verb.</Paragraph>
    <Paragraph position="6"> In the actual dependency analysis, we try to select the dependency structure ^T that maximizes the Equation (5) from the possible parses T for the inputted sentence:</Paragraph>
    <Paragraph position="8"> The proposed model is inspired by the semantic role labeling method (Gildea and Jurafsky, 2002), which uses the frame element group in place of the particle set.</Paragraph>
    <Paragraph position="9"> It differs from the previous parsing models in that we take into account the dependency relations among particles in the set of case elements that modify a verb. This information can constrain the combination of particles (cases) among bunsetsus that modify a verb. Assuming the independence among particles, we can rewrite Equation (5) as</Paragraph>
    <Paragraph position="11"/>
    <Section position="1" start_page="834" end_page="835" type="sub_section">
      <SectionTitle>
4.1 Syntactic property of a verb
</SectionTitle>
      <Paragraph position="0"> In Japanese, the &amp;quot;ha&amp;quot; case that indicates a topic tends to modify the main verb in a sentence and tends not to modify a verb in a relative clause. The  co-occurrence probability of the particle set therefore tends to be different for verbs with different syntactic properties.</Paragraph>
      <Paragraph position="1"> Like (Shirai, 1998), to take into account the reliance of the co-occurrence probability of the particle set on the syntactic property of a verb, instead of using P(rsi(T)|vi(T)) in Equation (5), we use P(rsi(T)|syni(T),vi(T)), where syni(T) is the syntactic property of the i-th verb in T and takes one of the following three values: 'verb' when v modifies another verb 'noun' when v modifies a noun 'main' when v modifies nothing (when it is at the end of the sentence, and is the main verb)</Paragraph>
    </Section>
    <Section position="2" start_page="835" end_page="835" type="sub_section">
      <SectionTitle>
4.2 Illustration of model application
</SectionTitle>
      <Paragraph position="0"> Here, weillustratetheprocessofapplyingourproposed model to the example sentence in Figure 1, for which there are four possible combinations of dependency relations. The bunsetsu combinations and corresponding sets of particles are listed in Table 1. In the analytical process, we calculate for all the combinations the co-occurrence probability of the case element set (bunsetsu set) and the co-occurrence probability of the particle set, and we select the ^T that maximizes the probability.</Paragraph>
      <Paragraph position="1"> Some of the co-occurrence probabilities of the particle sets for the verbs &amp;quot;aru-ku&amp;quot; and &amp;quot;hogosuru&amp;quot; in the sentence are listed in Table 2. How to estimate these probabilities is described in section 5.3. Basically, the larger the number of particles, the lower the probability is. As you can see in the comparison between {de,wo} and {de,de}, the probability becomes lower when multiple same cases are included. Therefore, the probability can reflect the constraint that multiple case elements of the same particle tend not to modify a verb.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>