<?xml version="1.0" standalone="yes"?>
<Paper uid="C90-3078">
  <Title>D~IGN ISSUE OF ECTST</Title>
  <Section position="1" start_page="0" end_page="0" type="metho">
    <SectionTitle>
D~IGN ISSUE OF ECTST
</SectionTitle>
    <Paragraph position="0"/>
  </Section>
  <Section position="2" start_page="0" end_page="0" type="metho">
    <SectionTitle>
ABSTRACT
</SectionTitle>
    <Paragraph position="0"> This note presents an overview of the English-Chinese Translalion System for Tourists (~I~q) currently under development at South China University of Technolo~/. A brief description of the bilingual dictionazv is given, followed by descriptions of grammar rules representation and the n~in processes involved in translation.</Paragraph>
    <Paragraph position="1"> S~TEM CONFiGUR&amp;TIOR ECTST consists of a translation program, a bili,4Tual diction~w and a rule-data base. The program body is composed of a sequence of modules, performing translation in four phases: SL sentence Initiation ~ Tt, sentence The initiation pha~e is concerned with input of the SL sentence, diotionsry look-up and morphological processing. The analysis phase involves syntactic and semantic parsing, which are accomplished through linguistic models and case frame. The transfer phase comprises rules for converting the parsed SL sentence into the TL sentence. ~e generation phase, applying the contents obtained from the previous process, generates the TL sentence.</Paragraph>
    <Paragraph position="2"> ECTST is implemented in PASCAL. The software is separated from the linguistic data, so that any language can be accepted if the grammar rules and vocabulary are given. Likewise, the system program are free to o:hange their components with no undue restrictions that may be imposed by the linguistic components.</Paragraph>
    <Paragraph position="3"> DIdTIONAPY= ~,ONT~PFS The dictionary is bilingual: it contains morphological, syntactic and semantic information needed for the analysis and generation of a sentence. This includes information about the category of words, their semantic fea~ tures and case frames. Entries in %he lexicon are of eight types, and their semantic features are based on graded concepts. The case frame provides a means to find out the logical relationship between components in the sentence.</Paragraph>
    <Paragraph position="4"> At present, the dictionary contains a limited set of lexical entries, which are grouped into models with the initial letter as the index for accessdeg</Paragraph>
  </Section>
  <Section position="3" start_page="0" end_page="376" type="metho">
    <SectionTitle>
GRAMMAR RUL~
</SectionTitle>
    <Paragraph position="0"> In ECTST, rules are represented in the form of meta-model. It may contain one or more data items as shown below: A \[~\](a) B FY\](b) C \[~3(c)  ~,'here #~B,C Pepresent in:Formation on caLe.~oz'y of the word, while x,ytz aald a, t h, c are parameters ind J. oatin~ multip\].e pieces of informat ion amd %z:ee stl.uoture ,~eparate\].y. In many oases semantic f'eatures or inf'ormatzon on ~qram:matioa\] ,'~eT4J.er~ number or ea,,~e ca.n i,e useO as para;'~etez~,:~.</Paragraph>
    <Paragraph position="1"> ,generally, hmxlreds or even thousamds of grm'm;ar rules are necessa~?/ for lan~1~.a.~e analysis \[~!d tramsforma, tion. I% is impr'aotical %0 check whether all these rules oa/% be applied to all intermediate processings. To make %he pro.certain:?/ effi&lt;~ien%,ru\] es ~z\]-e, qroupe@ into packe1:,s~ each degding wigh speci- null other, f'o:r ap2J.ioatior~ of o~:-;e fra.o.ePS, and so on /~n,~! ~,s; s &amp;re ,---,,-~i e, ~ -',- -~ :\['roTr~ JJ~\]e SLI\]?SeG~ s truoture %Lrou.d: %he de~c r-;irtlotur.e. A dee-~ Ptrt~etu.re ma~.;  comprise roles of siz e:'~entia\], types: SU\]!j eat, (.;:8J eat ~ \]~Vol,~ement, \[:: ITna%i on, ST/i.~e and CAU,~alion.o They make up a basic fra,me wit\]~ the ~%'EDic~tor as shown ~n F:j.~;o 1.</Paragraph>
    <Paragraph position="2"> In apPS1icstion, a. role rosy come into it. ~, subc-:~%eqories v,d&amp;quot;,er:,ever neoess~;, Slq'ua%ion, for e:&lt;amoie~ may fa_l\], into</Paragraph>
    <Paragraph position="4"> in analysis, the deep structure is obtained via preferei'~tial weightincc oacala.ted from ~rammatical data m~d frame labels. 'T}~e fo!lowi~c sent~noe~ for exa;nF,\].e would resul% in %'.co dif~ feren% intern~l s!ruotures even +-hough their slEPf&amp;oe struct1~res ~re sJ.mi\]ar.</Paragraph>
    <Paragraph position="5"> I. We found John ve~, well.</Paragraph>
  </Section>
  <Section position="4" start_page="376" end_page="376" type="metho">
    <SectionTitle>
2. We know John ve.~ ~ wello
</SectionTitle>
    <Paragraph position="0"> in the case frame, tLeir deep structures would be: When an intern~l strimture results, i% serves as the basin for transfer.</Paragraph>
  </Section>
  <Section position="5" start_page="376" end_page="377" type="metho">
    <SectionTitle>
TRM~SFF~ AND GIi~i~I~ATiON
</SectionTitle>
    <Paragraph position="0"> In the transfer sta~e, transformation is accomplished in two steps&amp;quot; firs% the internal structure of the Fi, senteuoe is generated into a tree, with nodes that indicate their proper memsntic and gr~r.atica\] order in th~ TL sentence; then lexicon rules arc invoked to transfer the SL entrT- ~ on the basis of its context, in%o %he TL entry. The advantage of such a procedure are obvious. It ~kes the r~u\].es more flexib!e9 especially those oopinC/ S with sentences with similar int ernal s tructl/res. Moreover p ~ es can be added, modified or changed as needed with no resultant effect on one another.</Paragraph>
    <Paragraph position="1"> When a target tree is built up, it is then scanned by way of left recursion  and with words appended to its terminal nodes a~ requireddeg Finally~ a oh~r~cter string is obtained; its output is ~ sentence in TL.</Paragraph>
  </Section>
class="xml-element"></Paper>