<?xml version="1.0" standalone="yes"?>
<Paper uid="C82-1062">
  <Title>The Transfer Phase in an English-Japanese Translation System</Title>
  <Section position="10" start_page="0" end_page="0" type="concl">
    <SectionTitle>
4. CONCLUSION
</SectionTitle>
    <Paragraph position="0"> We discussed in this paper mainly about the role of semantics in Transfer Phase by taking examples from our English-Japanese translation system.</Paragraph>
    <Paragraph position="1"> The following points should be made clear here.</Paragraph>
    <Paragraph position="2"> (I) We can distlnguishtwo kinds of semantics in natural language processings, that is, &amp;quot;semantics as meaning representations&amp;quot; and &amp;quot;semantics as constraints (or preference)&amp;quot;, both of which have their own analogues in linguistics, Logical Formula in MG and Selectional Restriction Rules based on semantic markers. Our contention in 2 is only that the former type of semantics is not so useful as often claimed. The latter could or should be included as descriptors in multi-level analysis trees. This is useful not only for reducing possible ambiguities in Analysis Phase but also for augumentlng the descriptive power of usage patterns in Transfer Phase.</Paragraph>
    <Paragraph position="3"> (2) We discussed about the utilization of usage patterns in Transfer Phase.</Paragraph>
    <Paragraph position="4"> However, they should be used also in Analysis Phase to reduce ambiguities.</Paragraph>
    <Paragraph position="5"> At present, only co-occurrence restrictions between predicates and specific prepositions are expressed by VL-i and utilized in Analysis Phase, but usage patterns of predicates here are much more rich, such as co-occurrence of specific lexical units (nouns, adverbs, etc.), of phrases with specific semantic and syntactic properties etc. Because these are highly idiosyncratic .and dependent on each predicate, how we can compromise these idiosyncratic matters with general rules in Analysis Grammar remains as one of important future problems.</Paragraph>
    <Paragraph position="6"> (3) We intensionally avoided the discussions about linguistic properties of deep cases. In fact, several grammatical rules can be founded on deep cases. By referring to deep cases, we can formulate, for example, a rule which decides whether passive construction is possible or not. Deep cases in this usage give linguistic classifications of relationships among predicates and noun phrases, but not those among events and objects in the real world.</Paragraph>
    <Paragraph position="7"> Deep eases of this type are, however, language-dependent as EASP and JASP (Rules of passivization in Japanese and English are different, for example), and therefore, we cannot use them as universal relationships in the intermediate representations. Moreover, even for linguistic deep cases, we think that it might be more practical to use the other kind Of markers such as markers directly showing the possibility of passivization etc.</Paragraph>
    <Paragraph position="8"> (4) Though DASP is claimed to be universal, this claim should be verified in future by applying it to other language pairs. In fact, the values of DASP reflect many properties specific to English and Japanese. That is, we set up the values of DASP only to distinguish the aspectual features (of real world events) which lead to different surface aspectual forms of English or Japanese. These should be distinguished in order to transfer aspectual expressions appropriately. Other languages might express explicitly in surface forms different aspectual features of events from differnt points of view. Because of this language-dependent property of DASP, we perform both the interpretation of ESASP and the determination of JSASP in Transfer Phase.</Paragraph>
  </Section>
class="xml-element"></Paper>