<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1050">
  <Title>Analysis of Scene Identification Ability of Associative Memory with Pictorial Dictionary</Title>
  <Section position="4" start_page="310" end_page="311" type="intro">
    <SectionTitle>
2 Scene Identification
</SectionTitle>
    <Paragraph position="0"> In order to identify spatial scenes lmsed on inl)ut sentenees, some kind of information &lt;&gt;f detining each seell(~ must exist. As exph'dned in the OPEl), &amp;quot;The dictionary is edited regarding the depiction of (weryday objects and situations, in order to allow greater scope for the treatment of these, objects and situatiovs in the context of English-speaking countries&amp;quot; \[from l;'of ward in OPED\]. Each scene or pictorial entry i~, the OPED accompanied by a word list of entries f,'om the scene (see next section). This bu,ldle of infi)rmation is the basis for organizing our associate memory model.</Paragraph>
    <Section position="1" start_page="310" end_page="310" type="sub_section">
      <SectionTitle>
2.1 Constraints
</SectionTitle>
      <Paragraph position="0"> Here we ~msume some constraints on the method of representing and using the OPED scenes: * Only ordinal livivg scenes (384 scenes in(:lu(ling thousands of subseenes) are handled. All scenes are hypothesized to be eonstructable by combinations of these scenes.</Paragraph>
      <Paragraph position="1"> (r) Most of the words in OPEl) are noun terms aeeoml)anied by adjective terms. In this system, spatial-seenes are identified by using only these words. No syntactical information is used.</Paragraph>
      <Paragraph position="2"> * Compound words are dec&lt;)mposed into primitiw'.</Paragraph>
      <Paragraph position="3"> words.</Paragraph>
      <Paragraph position="4"> * The associative memory luus the ability to incrementally learn, but our analysis here uses a tixed set of scenes and words.</Paragraph>
      <Paragraph position="5"> .................................. ,Saqu~tlal mymbol Direct Logical 1 \[ r ...... t .... uo</Paragraph>
      <Paragraph position="7"/>
    </Section>
    <Section position="2" start_page="310" end_page="311" type="sub_section">
      <SectionTitle>
2.2 PDAI&amp;CD and WAVE
</SectionTitle>
      <Paragraph position="0"> The spatial scene identification system analyzed in this paper is one moduh' of a general infi'rence architecture called l'aralM l)istributed Associatiw.&amp;quot; Inference and Contradiction /)etection (PDAI&amp;CD)(Tsunoda '\['. and 'Fanak;t l\[., 1993), which uses an :msociatiw~.</Paragraph>
      <Paragraph position="1"> memory WAVE('\['sunoda T. an(\[ Tanaka H.) lmsed on neural networks and a logical veritieation system. We haw~ previously presented itll application of that architecture to semantic C/lisambiguation (Tsunoda T. and Tanalat II., 1993). It features a eognitive model of fast disambiguation depending on context with bottom-up associatiw:, memory together with a nmre precise top(lown feedba(:k process (Fig.l). After one scene is selected by previously inlmt words, the system can disambiguate meaning of following words (as in the right side of Fig.2). In the. future, we plan to combine natural language proce.ssing with visual image from sensory data. Our representation of the spatial data fi'om the OPED is considered to be a simplest approximation of such visual sensory images.</Paragraph>
    </Section>
    <Section position="3" start_page="311" end_page="311" type="sub_section">
      <SectionTitle>
2.3 Semantic Disambiguation
</SectionTitle>
      <Paragraph position="0"> Words in OPED have ditferent meanings corresponding to their use in ditferent scenes. When a set of ambiguous words uniquely determines a scene, we conclude that the words have been successfully disambiguated. We acknowledge that many other processes may be involved in general word sense disambiguation, but use this scene-selection sense of word sense (lisainbiguation from here on.</Paragraph>
      <Paragraph position="1"> We illustrate typical two examples below. The system with OPED and our associative memory can re(:ognize these sentences and classify into each scene in the dictionary. Once a scene is identified, it assigns each ambiguous words uniquely. We call it semantical disambiguation of words here. The correspondances of the sentences and each meaning of word is summarized in Table.1.</Paragraph>
      <Paragraph position="2">  1. ball (a) (b)  Tom shot a white cue ball with a cue. The ball hit a red object ball and he thought it's lucky if it will ...</Paragraph>
      <Paragraph position="3"> Judy found that she was in a strange world. Devils,dominos,pierrots,exotie girls, pirates,.*, where am I? 'Oh!', she said to herself, a.s she found she wandered into a ball,  2. lead : (a) It's not sufficient to shield only by the lmthick concrete* The fission experiment requires additional 10cm-thick blocks of lea&lt;l. Fission fragments released by the chain reaction of...</Paragraph>
      <Paragraph position="4"> (b) He said to his son, &amp;quot;Please pull out the plug  of the coffee grinder from the wall socket. Be careful not to pull by the lea&lt;l. Ituum...here I found the kettle.&amp;quot;...</Paragraph>
      <Paragraph position="5"> Our system is able to disambiguate each meaning in these examples actually.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>