<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-2113">
  <Title>A Method of Utilizing Domain and Language specific Constraints in Dialogue Translation</Title>
  <Section position="4" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Idiosyncratic Gaps between
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
two Languages
2.1 The Problem
</SectionTitle>
      <Paragraph position="0"> For instance, in Japanese a verb may have certain number of complements (or the verb has its own va lency). Those complements are often eliminated if they are already known as old information. When honorific expressions (respective, condescend, polite) are used, a certain kind of the ellipses (zero-pronouns referring the speaker or the hearer) can be resolved by using these key expressions in many cases. \[I\] However, there are another sort of utterances which lack substantial words and are difficult to understand individually. As a target of our examinations, we selected an expression called &amp;quot;dr-expression&amp;quot;. Though there are a lot of variations for da-expressions\[14\], we consider one of their types that has a structure : Copula(A, B). It means that A and B is identical (in a certain sense). In many cases, we cannot translate such a dr-expression without knowing the context where the utterance is spoken.</Paragraph>
      <Paragraph position="1"> Our current target domain for dialogue translation is &amp;quot;conference registration task&amp;quot;. The example ~ntenses referred in this article arc from the doinain.</Paragraph>
      <Paragraph position="2"> Suppose that the following Japanese utterances should be translated.</Paragraph>
      <Paragraph position="3"> 31: sankaryou wa donoyouni shihavae (~e) (topic) (how) (pay) bayoi deshou ka. (acceptance) (copula) (inter~'ogation) 32: saatkaryou wa ginkou-furikomi desu*.</Paragraph>
      <Paragraph position="4">  Tile t~aturc structures of J 1 and J2 are as FS-J 1 and FS-J2) The literal translation of J2 may be : E2: The (attendance) :fee is bank-transfer.</Paragraph>
      <Paragraph position="5"> Of course this English sentence is not acceptable in ordinary situations. Accordingly a certain way of eomplementation is required. There can be several alternatives and it might be difficult to choosc one appropriate expression among them. For instance, J2 could be translated in various ways if such a eomp\]ementation is performed.</Paragraph>
      <Paragraph position="6"> E2a: The payment should be made by bank-transfer.</Paragraph>
      <Paragraph position="7"> E2b: Please pay by bank-transfer.</Paragraph>
      <Paragraph position="8"> E2e: Would you please pay by bank-transfer? \[agen !X73 \[obje !X6\[\[parm !X4\[\]\] \[restr \[\[reln SANKARYOU-a\] \[entity !X4\]\]\]\]\] \[mann !X9\]\]\]\]333\]\] FS-J1. Analysis Result of J1 iThese feature structures are partially modified for explanation. AcrEs DE COLING-92, NANTES, 23-28 AOUi' 1992 7 5 7 I)gOC. OF COLING-92, NANTES, AUG. 23-28, 1992 There are some Japanese expressions (typically &amp;quot;da-expreasions&amp;quot;) which lack a substantial word(s) known for tile dialogue participants. In the previous example sentence J2, the substantial words are : sankaryou(fee) and ginkou-furikomi(bank-transfer). The word sankaryou is the Theme 2 of this utterance and it is already known (old information) in the previous utterance. And the word &amp;quot;shiharau&amp;quot; does not appear in J2, while it appeared in J1..12 is a typical da-expression (a kind of copula sentence) in Japanesefl\[14\] The Rheme 2 of the sentence J2 is obviously ginkoufurlkoml (bank-transfer) and it meets the focus of the previous question J1. Accordingly the utterance J2 satisfies the Grice's maxim of informativity. In English, however, we can't say &amp;quot;The fee is hanktransfer.&amp;quot; Wc have to elaborate the utterance with some substantial or functional words.</Paragraph>
      <Paragraph position="9"> Generally such kinds of knowledge for elaboration have been provided with domain knowledge which are commonly accessed by respective processing modules.</Paragraph>
      <Paragraph position="10"> We propose that the concept of Mel'~uk's lcxieal functions can be extended for designing special sets of domain-dependent lexieal functions. This idea is as follows.</Paragraph>
      <Paragraph position="11">  our dialogue corpus.</Paragraph>
      <Paragraph position="12"> The structure PS-E2 could yield two sentences : The fee is paid by bank-transfer.</Paragraph>
      <Paragraph position="13"> You pay the fee by bank-transfer.</Paragraph>
      <Paragraph position="14"> lIowever, it is still unnatural because the speaker's intention doesn't appear in these sentences. Therefore another elaboration is needed for producing a more sophisticated utterance.</Paragraph>
      <Paragraph position="15"> The previous utterance J 1 is apparently a question that demands a value referred with the interrogative &amp;quot;donoyouni&amp;quot; (how). During our pre-transfer phase, an Illocutionary Force Type (IFT) of tile given sentence is extracted.t7\] In this case, the IFT of J1 is determined ~us QUESTIONREF.</Paragraph>
      <Paragraph position="16"> So far the assignment of IFTs was decided with matching surface expressions. Accordingly tile IFT of J2 is first recognized ms INFOI1.M (default IFT), becanse the predicate DA-identlcal (colmla) does not specify any explicit intention.</Paragraph>
      <Paragraph position="17">  For translating the above mentioned da-expressions we have to cnnlp~eu*ent apl)rol)riate substantial words, which are rclatively domain dependent.</Paragraph>
      <Paragraph position="18"> * Knowlede on IFT Though the system of IF'l? was formerly thought to be lauguagc mdependcnt, this as smnption turned out too naive. We *low consider that therc can be some situations where a tra*lsfer of IFT is required, according to the language dependent strategies of producing utterances.</Paragraph>
      <Paragraph position="19">  When wc limit the target, domain of translation, the associate knowledge is also restricted. I\[owcver, wc have to be eareflll that even in such a presupposition some general knowledge (recta knowledge) is indispensable to make elaboration tbr elliptical sentences.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.1 Domain knowledge
</SectionTitle>
      <Paragraph position="0"> Within our task domain, we have some kinds of enlpirical knowledge of &amp;quot;registration for a confer cnee&amp;quot;. Wc observe several frequent verbs with specifically Ciominant eooccurrenee of nouns. Thougb these nouns do not always appear explicitly, we carl assume their existence in the background of utterances.</Paragraph>
      <Paragraph position="1"> l'br example, we can describe preferable candidates of complements which have strong relationships with a verb &amp;quot;pay&amp;quot; in our target domain, 5 The italic letter symbols indicate eoneeptnal categories.</Paragraph>
      <Paragraph position="2"> pay object - (attendance) fee, amoun~ of money pay agent dialogue pavticipanl(speaker / imarer) pay manner -- bank-transfer, credit card, in cash pay - time-destination - date, deadline Here we define a set of domain dependent knowledge after tim notation of lexical fimctions proposed by Mel'~uk\[8\].</Paragraph>
      <Paragraph position="3"> Obje(pay) ::C/. fee</Paragraph>
      <Paragraph position="5"> Note that the above descril)tions have a direction.</Paragraph>
      <Paragraph position="6"> The righthand symbols can be conceptual categories.</Paragraph>
      <Paragraph position="7"> Then the relationship between fee and bank-transfer can be obtained thro|lgh an indirect path. Such kiuds of knowledge can be extracted semi-automatically from our dialogue corpus, to'u certain extent.</Paragraph>
      <Paragraph position="8"> ,3.2 Language specific strategies of producing utterances It is natural to consider that there exist eertaiu language specific strategies of producing ut*erances, il&gt; tuitively fro|n the prevk)us example dialogue, in other words, sonic Iangue*ge dependent coInnnluicative structures are recognized. Pragmatic constraints are derived from the difference of eommunieatiw~ strategies with languages. So far, this importance has been relatively less regarded eonlpared with other linguistic aspects in trauslation.\[2\] 5Thongh we do llOt ment.iml hm'e, it is signilicant for lllcdicLion of words for sp~l:h-to=Sl)cech translation systellls. hi Japane,~ dialogues, tile speaker's intention tends to appear in tire sentence final expressions emd it is quite often rendered indirectly.</Paragraph>
      <Paragraph position="9"> a2: sankaryou wa ginkou-furikomi desu*.</Paragraph>
      <Paragraph position="10"> This is a neutral da-expression and there is no additional information other than indication of the method of payment. Ilowew~r, the following exampies includes some special nuances in their final expressions. Both of them are quite natural as responses to the qnestion J 1.</Paragraph>
      <Paragraph position="11"> J2a: sankaryou wa ginkou-furikomi to naZte oriraasu, (polite da-expression) J2b: sankaryou wa ginkou-fur+-kom+de onegai shimasu. (polite request) We think that these Japanese utterances are equivalent under the given situation (or tile communicative goal). In any cases, the method of payment is desig nated. The point is how it should bc communicated.</Paragraph>
      <Paragraph position="12"> We can assume the attitnde of the speaker is kept consistent in principle. The translation shonld also follow this rule, especially in ca.ue of the utterances by the secretary of the conference. It couhl affect the style of expressions. In faet, we found many 1N-FORM utternces really mean indirect REQUEST.</Paragraph>
      <Paragraph position="13"> The indirectness is remarkable in Japanese (using da-expressious) and a direet translation can be abrut)t or not informative, partly because there seems to be no polite copula expressions in Ellglish. Therefore, a certain transfer of IFT might be required.</Paragraph>
      <Paragraph position="14"> We have to consider some constraints for al)plying such a rule. In this case, the IFq' of the previous utterance (Q\[II,',STIONRI'~F) should be known. Additionally the focus of the question is needed. Furthermore, thesaurus knowledge about predicates and complements might I)e referred.</Paragraph>
      <Paragraph position="15"> a.a Incorporating two kinds of constraints null In our dialogue translation system, a feature structure rewriting systeln(llWS) ~; is used \['or transferring between I:,l)anese and English.\[3\] An el\]ieient control mechanism l;:)r rewriting rules in the IONS is realized using ltew~'tling 1;'nvironmenl and Application Coustrainls. null The Rewriting Environment(RE) is introduced in order to control rule apphcation and to maintain rule lLexibility alld modularity. Each I~.E is composed of a conlbiliatioll of paranleters and their values, which provides the condit.ion of rewriting and is dynamically changed through the transfer processing.</Paragraph>
      <Paragraph position="16"> ~1~ has been exterMed for introdlming a type system &amp;lid a pl e\[el'e lice Illed~;~ltlsln.</Paragraph>
      <Paragraph position="17"> ACRES DE COLING-92, NAtal, S, 23-28 not)r 1992 7 5 9 I'ROC. OV COL1NG-92, NANTES, AUO. 23-28, 1992 Each rewriting rule has its specific application constraiuts(AC). When the ACs unify with the RE in a certain phase, the appheation of the rule fires. Thus, the transfer process is procedurally performed, according to the REs. This allows individual rules to be rather declarative and include few procedural decisions for lexical choice.</Paragraph>
      <Paragraph position="18"> We implemented the rules that contain domain and language specific constraints, extending this RWS.</Paragraph>
      <Paragraph position="19"> Several example rule are shown below. 7</Paragraph>
      <Paragraph position="21"/>
    </Section>
  </Section>
class="xml-element"></Paper>