<?xml version="1.0" standalone="yes"?>
<Paper uid="C65-1022">
  <Title>SENTENCE GENERATION BY SEMANTIC CONCORDANCE</Title>
  <Section position="3" start_page="22" end_page="22" type="intro">
    <SectionTitle>
2. EVALUATION OF THE GENERATED SENTENCE
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="22" end_page="22" type="sub_section">
      <SectionTitle>
2.1 Evaluation of the generated sentence -syntax-
</SectionTitle>
      <Paragraph position="0"> Several methods are developed for the description of sentence structure.</Paragraph>
      <Paragraph position="1"> We represent the syntax of English by a phrase structure grammar, transformational grammar, and mophophonemic rules. The kernel sentence is generated by the phrase structure grammar, then some proper transformational rules are applied to it, and then the modification of the sentence by the morphophonemic rules produces the final output.</Paragraph>
      <Paragraph position="2"> These rules should generate &amp;quot;conceivable sentence structures&amp;quot;, although the actually used sentence structures have several constraints. These are for example, (i) the depth of the sentence structure (ii) the coordination structure (iii) the intrinsic unsymmetry of sentence structure --- progressive structure, top heavy structure etc.</Paragraph>
      <Paragraph position="3"> In general the rules which are suitable for analysis of a given sentence seem to differ from the rules which generate good sentences. The difference between these two is the difference between the actual spoken sentences and the conceivable sentences. Here we can see man's tendency to the language structure. Therefore it will not be worthless to know the frequency ratios of the phrases used in the actual sentences.</Paragraph>
    </Section>
    <Section position="2" start_page="22" end_page="22" type="sub_section">
      <SectionTitle>
2.2 Evaluation of the generated sentence -semantics-
</SectionTitle>
      <Paragraph position="0"> The next question, and the more difficult one than the former, is the determination of what is the proper meaningful sentence. The test for the semantic sentence anomaly is far more difficult than the test for the grammaticality of the sentence. Here we can think of the following three levels of criteria for the right sentence.</Paragraph>
      <Paragraph position="1"> (i) The grammatical sentence which is spoken or written by the average person (and the sentence which conveys a concrete concept without knowing the circumstances the sentence is spoken). Here &amp;quot;grammatical&amp;quot; covers the phonology, phonemics, morphology, syntax etc. These sentence which are grammatical but which are contradictory in meaning and which we do not speak are to be rejected.</Paragraph>
      <Paragraph position="2"> (ii) The sentences which are incomplete in the word usages, inflexions and so on but which convey clear understandable concepts. These are the so-called corrigible sentences.</Paragraph>
      <Paragraph position="3"> (iii) The sentences which are grammatical but carry no concrete meaning Sakai &amp; Nagao 3 if they are not supplemented by tediously long explanations about the righteousness of the expression.</Paragraph>
      <Paragraph position="4"> We have here adopted the second criterion for our generation of English sentences. That is because we can transform the corrigible sentences into the complete ones comparatively easily by checking the concordance of gender, number, case etc. Hereafter we are mainly concerned with the sentence which carries very definite concept, that is to say, the sentence of complete semantic consistency.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>