<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1004">
  <Title>Learning Dependencies between Case Frame Slots</Title>
  <Section position="2" start_page="0" end_page="20" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> We address the problem of automatically acquiring case frame patterns (selectional patterns) from large corpus data. The acquisition of case frame patterns normally involves the following three subproblems: 1) Extracting case fl'ames from corpus data, 2) Generalizing case frame slots wMfin these case frames, 3) Learning dependencies that exist between these generalized case frame slots.</Paragraph>
    <Paragraph position="1"> In this paper, we propose a method of learning dependencies between case frame slots. By</Paragraph>
    <Section position="1" start_page="0" end_page="20" type="sub_section">
      <SectionTitle>
*Real World Computing Partnership
</SectionTitle>
      <Paragraph position="0"> 'dependency' is meant the relation that exists between case frame slots which constrains the possible values assumed by each of those slots. As illustrative examples, consider tile following sentences. null The girl will fly a jet.</Paragraph>
      <Paragraph position="1"> This aMine company flies many jets.</Paragraph>
      <Paragraph position="2"> The gM will fly Japan AMines.</Paragraph>
      <Paragraph position="3"> *The airline conlpany will fly ,Japan Airlines.</Paragraph>
      <Paragraph position="5"> We see that an 'airline company' can be the sub-ject of verb 'fly' (the value of case slot 'argl'), when the direct object (the value of ease slot 'arg2') is an 'airplane' but not when it is an 'airline company '1. These, examples indicate that the possible values of case slots depend in general on those of the other case slots: that is, there exist 'dependencies' between different case slots. The knowledge of such dependencies is useflfl in various tasks in natural language processing, especially in analysis of sentences involving multiple prepositional phrases, such as The girl will fly a jet fl'om Tokyo to Beijing. (2) Note in the above example that the case slot of 'from' and that of 'to' should be considered dependent and the attachment sit(.&amp;quot; of one of the prepositional phrases (case slots) can be determined by that of the other with high accuracy and confidence. null There has been no method proposed to date, however, that learns dependencies between case frame slots in the natural language processing literature. In the past research, the distributional pattern of each case slot is learned independently, 1 One may argue that 'fly' has different word senses in these sentences and for each of these word senses there is no dependency between the case frames. Word senses are in general difficult to define precisely, however, and in language processing, they would have to be disambiguated Dora the context ~nyway, which is essentially equivalent to assuming that the dependencies between case slots exist. Thus, our proposed method can in effect 'discover' implicit word senses fi'om corpus data.</Paragraph>
      <Paragraph position="6">  and methods of resolving ambiguity are also based on the assuml:ition th.at case slots are independent (llindle and Rooth, 1991), or dependencies lmtween at most two case slots are considered (Brill and Resnik, 1994). Thus, provision of an efl'ective method of learning de, pendencies between (;as(; slots, as well as investigation of the usefulness of the acquired dependencies in disambiguation and other natural language processing tasks would be an inll)ortant contributiota to the fie.ld.</Paragraph>
      <Paragraph position="7"> In this paper, wc view the problem of learning (;as(? frame patterns as that of learning a lnulti-dimensional discrete joint distribution, where raw doni variables represent case slots. We then formalize the dependencies between case slots as the probabilistic dependencies betweeit these ralldoiil variables. Since the illllllber Of dependencies that exist, in a nmlti-dimensiona.l joint disl.ribution is exponential if we allow n-ary dependencies in general, it is int&gt;asible to accurately esi.itllate them with high accuracy with a data size available in practice. It is also clear that relatiw;ly few of these ra.ndom variahles (case slots) are actually depeitdent on each other with any signiticance. Thus it is likely that the target joint distribution can be approximated reasonably well by the product of component distributions of low order, drastically reducing the nuniber (:if paralneters /.hat need to be considered. 'Fhis is indeed the apl&gt;roach we take in this lmper.</Paragraph>
      <Paragraph position="8"> Now the probleni is how to approxilnal,e a ,joint distribution by the product of lower or&lt;ler compOlletit distributions, llecently, (Suzuki, 1993) l)roposed a.ii algorithnl to approxhnal.cly learii a lnulti-dimensional joint distribution exlwessible as a 'dendroid distribution', which is both efticient and tlworet, ica.ily so/lnd. ~,.Ve employ Suzuki's algorithm 1,o learn case fralim patterns ;is dendroid distributions. We conducted sollle experinlelits to automatically acquire case fi'alne patterns from the Penn 'Free Bank bra.cketed corpus. Our experimental results indicate that for seine class of verbs the accuracy achiew?d ill a disa.nlbiguni.ion experinlent can be inlproved by using the acquired knowledge of dependencies between case slots.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>