<?xml version="1.0" standalone="yes"?>
<Paper uid="C88-2142">
  <Title>Dialogue Translation vs. Text Translation -Interpretation Based Approach-</Title>
  <Section position="3" start_page="688" end_page="690" type="metho">
    <SectionTitle>
2 Differences of Environments
</SectionTitle>
    <Paragraph position="0"> In the current states of the art in machine translation, most researchers may agree that we cannot expect an ideal FAMT system which can translate any linguistic materials in any subject domains. So, at present, what should be discussed about MT systems have to be engineering problems.</Paragraph>
    <Paragraph position="1"> We should discuss problems from engineering points of view. That is, we should discuss, first of all, what types of systems or system organizations are economically and technically feasible in what situations of actual translation, and what sorts of human aids can be expected in real application environments.</Paragraph>
    <Paragraph position="2"> The important consideration is how to design feasible MT systems which can be used in actual, rather specific, translation environments. Different application environments require different technologies. Therefore, the questions we would like to pose in this paper are: (r) Which is more feasible in actual application envi~ ronments, dialogu e translation systems or textual translation systems ? ,., ()~m ,ee design a feasible dialogue translation system iu.~t by extending or modifying current MT tech~,ologies dew'loped exclusively fur textual translation ? Our an:~wer tothe first question, though it might sound sirs.age, is that diah)gue translation :ffstems of certain ~ype.~; are more feasible than textual translation systems which are ( urrently developed aud connnereially a,vailable. ~i, might b:~' the case that we imagin dialogue translation is ea:;ier, t ecause we have been engaged in developing a t( xPS1~d ~,ranslatiou system ~md have recognized many, not o~dy diiiicl,lt but ala~ m~ty a~d dirty problems iu textual tra,slatiou systems (\[Nakamura86\]).</Paragraph>
    <Paragraph position="3"> l~ut ned only because of that, we believe dialogue trans-I~,tioi~ syst:..ms are more feasible, mainly because of the ba~sic diffe~eu(:es of environments where these two tyl)e~; of systems will be used.</Paragraph>
    <Paragraph position="4"> We can summarize the differences of environments in wMch th(',e two types of systeuts might be used as fbllows. ~, Clear Deflnifiou of lnfo',malio'n : In certain types of di~,.logue translations, we can define rather clearly what iuformaliou should be transmitted tiom source se:atea(:es to target translations, while we generMly cannot in textual translation.</Paragraph>
    <Paragraph position="5"> By c~:rtain types of diMogues, we mean here the dialogues such as dialogues for hotel reservation and coul:erence registration which are currently picked up by the ATR research group, dialogues between patients and doctors tried by the CMU group (\['romita86\]), etc.</Paragraph>
    <Paragraph position="6"> o Actiw~ Pavlicipalious o\] Speakers and Hearers : in most application environments of textual n~ansla lion .,~ystems, they are supposed to be used by pTv= \]?ssio',al ~','a~tslalo'rs. We camtot have the writers of te~.:ts at the time of translatioxi, the persons who prel)~.rc texts and really want to comnmnicate ,~x)rn~ thing through the texts. The actual readers of trausluted texts are not awdlable, either, at the time of the translation, who.really want to get messages or iufor, aatiou eucodM in the texts.</Paragraph>
    <Paragraph position="7"> On tim contrary, in diMogue translation, we have bo~l, ~he speakers (the senders of messages) and the hearers (the receivers of me, ages) at the time of translatiiig m('ssages.</Paragraph>
    <Paragraph position="8"> These two differences make, we claim, dialogue traitslation systems more feasible in actual translation environments, if they are properly designed ibr taking these adwmtages.</Paragraph>
    <Paragraph position="9"> Our answer to the s(~ond question is directly derived ti-om the above discussion. That is, in ordel)to take the advantages of dialogue translation, the system organizations should be different ti'om those for textual translation. Mere extension of current Mr\[ ` tec|mologies for textual tl:anslation will not result in high quality dialogue translation systems by which ordinary people (:a~t communicate with eact, other.</Paragraph>
    <Paragraph position="10"> We will discuss what implications the basic differences of enviroments have in the design of dialogue translation systems and, substantiate the conclusion that i\] they are properly designed, cerlain types of dialogue Iranslation syMems, are more feasible, tex:hnically at least, than the text translation systems which are currently available.</Paragraph>
    <Paragraph position="11"> 3 What should be translated ? Fig. 1 shows a simplified framework of application systems of natural language understanding (NLU) other than MT systems. In this framework, understanding of a ~eno leuce is regarded as a process of transformation from an input sentence, a linear sequence of words, into so-called the meaning represeulalion of lhe senleuce.</Paragraph>
    <Paragraph position="12">  NLII hppl lcat ion Systet~s Memdng representation in this framework is tile input to certain internal processings such as deductive in: ferences, problem solvings in certain restricted domains, data base accesses, etc., which are actually implemented as computer programs to carry out certain specific internM tasks.</Paragraph>
    <Paragraph position="13"> Meaning of input sentences are defined in this fi'arnc~ work, relative to the internal tasks that the systems are  expected to perfor m. In other words, what kinds of information should be extracted from sentences are predefined, depending on the aims of the internal processings of the systems. Understanding is regarded as art extraction process of information relevant to specific internal tasks.</Paragraph>
    <Paragraph position="14"> However, the internal task or the aim of translation is to re-express by using sentences of target languages the information of all aspects conveyed by sentences of source languages, with as least distortion as possible(\[Tsujii86\]).</Paragraph>
    <Paragraph position="15"> The internal task of MT, by itself, does not define what information should be extracted from input texts.</Paragraph>
    <Paragraph position="16"> It is commonly recognized by linguists that all different surface linguistic expressions convey different meaning. MT systerns, at least textual translation systems, have to extract all the factors relevant to the determination of surface linguistic expressions.</Paragraph>
    <Paragraph position="17"> Most of the difficulties peculiar to MT, such as the so lection of appropriate target lexical items or expressions, etc. come from the fact that we cannot define in MT what aspects of information in source sentences are relevant to the determination of target expressions and should be extracted from source sentences* In general, we cannot establish a representational framework which is language universal and by which understanding results are represented. null As a consequence, most of the current systems use certain, linguistic levels of structural descriptions of source sentences, such as deep case structures in the Mu project, in order to calculate appropriate target descriptions. Because the structures are far from representing understandtug results and reflect the linguistic strutures of source sentences, their translation results are inherently struclure bound.</Paragraph>
    <Paragraph position="18"> On the other hands, in certain types of dialogues, we can define by the purpose of dialogues what is essential or important information conveyed by uttranees and should be transmitted to their translations. Here, we do not discuss about the systems which are capable of translating arbitrary dialogues like chatterings among house wives without any purposes, but the systems which translate dialogues of certain restricted domains as already mentioned, such as dialogues for hotel reservation, conference registration, etc. In such dialogues, we can define important information by referring to the aim of the dialogues. Such important information should be extracted kom  the input and properly transmitted to the target. So, the framework for dialogue translation becomes similar to that of the other applications of NLU illustrated in Fig. 1. We can introduce a layer of explicit understan&amp; in~ to MT systems, to which important information of nntterances are related and so, in which results of understanding can be represented in a language independent (but task dependent) way (\[Tsujii87\]).</Paragraph>
    <Paragraph position="19"> Some parts of utterances which convey information *mporlant for the purposes of the dialogues are related to this layer and interpreted. Because information is expressed language-independently in this layer, we can expect less structure bound translation results for the parts of utterances. On the other hand, the other parts which do not convey important information need not be related to this explicit understanding layer. They would be translated by conventional MT technologies.</Paragraph>
    <Paragraph position="20"> Let me show you a simple example from hotel reservation dialogues, which actually appears in the experiments conducted at ATR.</Paragraph>
    <Paragraph position="21"> lax 1\] \[Japanese\] hoteru( holel)-wa, tomodachi(friends)to Disuko( discotheque)-ni ikitai(t0 waut to go )-node, Roppongi(Roppongi - the name of the place in Tokyo)-no chikaku(t0 be near )-ga iino(t0 be good)-desuga ? \[Structure Bound English Translation\] As for hotel, because \[ I \] would like to go to Discotheque with friends, to be near to Roppongi is good.</Paragraph>
    <Paragraph position="22"> \[English Translation\] Because I would like to go to discotheque with friends, I prefer to stay at a hotel near to Roppongi.</Paragraph>
    <Paragraph position="23"> In this example, we can divide the utterance into two.</Paragraph>
    <Paragraph position="24"> One is the part which contain important information for hotel reservation, and the other is the part which does not. Because the location of the hotel which the client wants to stay is important for the task of hotel reservation, the underlined part of the uttrance is important and should be translated as properly as possible.</Paragraph>
    <Paragraph position="25"> The other part of the utterance, which gives the l:eason why the client wants to stay at a hotel in a specific region of Tokyo (Roppongi), is less important. Our contention is that these two parts of the utterance should be treated differently in dialogue translation systems.</Paragraph>
    <Paragraph position="26"> Note that the English translation given above has a deep case structure completely different from that of the source sentence. The translation contains the verbs to prefer a~nd to slay whose corresponding Japanese verbs do not appear in the source sentence.</Paragraph>
  </Section>
  <Section position="4" start_page="690" end_page="691" type="metho">
    <SectionTitle>
4 Architecture of Dialogue Trans-
la.l;ion Systems
</SectionTitle>
    <Paragraph position="0"> Fig. 2 shows a schematic view of a system which translates dialogues in a certain restricted domain. The translation system tmows in advance what kinds of information el concepts ~zre important for the natural flow of dialogues in thai. specific task domain, and also knows a set of surface linguistic expressions which may convey such important  ........ For the laportant Parts ...... For tile less important Parts I:ig. &amp;quot;2 fhe 0rgaaizati0n of a Dialogue Traaslatl0n 3yste~ By truing these kinds of knowledge, the system should be able to distinguish the parts which convey important informational contents extract them and relate them to the repres:entations of the explicit understanding layer. It is certainly difficult to capture the important parts of untter~mces and understand them, but if we confine ourselves to a certain restricted task domain, it is much easier than story understandings in general, which A1 re~ searchers have been interested in.</Paragraph>
    <Paragraph position="1"> Furthermore, it is easier than developing intelligent dialogue systems which make conversations with lmman users in restricted task domains, for example, to make appropriate hotel reservation. Although those intelligent systems should be able to understand fully the u~r's utterances, a dialogue translation system needs not. The hearer, the receiver of the translated messages may un~ derstand tile speaker's intention. A translation system is only required to provide information sufficient for his understanding. It is desirable but not inevitable for a dialogue tarnslation system to have the ability of recognizing the speaker's plan.</Paragraph>
    <Paragraph position="2"> A translation system which extracts intporlaut in/of mutton from source utterances and re-expresses it in the target language can produce less structure bound translations. It can reduce varieties of surface expressions to a single meaning representation, if they convey essentially the same information, the same from the view point of the purposes of dialogue. For example, the tbllowing Japanese expressions, which have quite different (deep case) structures, may be reduced to a single representation and re-expressed by English expressions. The English expressions will be chosen independently of Japanese strueture.'~ but only by considering English contexts where the ex-pressions are located.</Paragraph>
    <Paragraph position="3"> \[Ex 2\] \[Japanese\] Roppngi-no chikaku (to be near) -no hoteru (hotel) -gaii (to be good) wa.</Paragraph>
    <Paragraph position="4"> \[Structure bound translation\] A hotel near to Roppongi is good.</Paragraph>
    <Paragraph position="5"> \[Japanese\] Ropponi-atari (around) -no hoteru (hotel) -we onegaishimasu (please).</Paragraph>
    <Paragraph position="6"> ---* \[Structure bound translation\] A hotel around Koppongi, please.</Paragraph>
    <Paragraph position="7"> \[Japanese\] hoteru (hotel)-ha roppongi-no chikaku (to be near) -ga iinodesuga (to be good) \[Structure bound translation\] As for hotel, to be near to Roppongi is good.</Paragraph>
    <Paragraph position="8"> \[Japanese\] tsugou-ga-iino (t0 be convenient)ha roppongi-ni chikai (to be near) hoteru (ho~ tel) desuga.</Paragraph>
    <Paragraph position="9"> \[Structure bound translation\] What is convenient is a hotel near to Roppongi.</Paragraph>
    <Paragraph position="10"> As an extreme, we can imagine a system which produces fluent translations only for important parts of utterances but awkward ones for the other parts.</Paragraph>
    <Paragraph position="11">  \[~:x a\] \[Because (to Go Discotheque) Friends\] I prefer to stay at a hotel near to Roppongi.</Paragraph>
    <Paragraph position="12"> Note that a dialogue translation system needs not understand utterances completely, and so, it needs not understand why the clause 'tomodachi-to disuko-ni ikitai'(I would like to go to discotheque with friends) can be the reason tbr staying at a hotel near to Roppougi. ~lb understand this, a system has to have a lot of real world knowl-edge which is not so closely related with hotel reservation tasks, such as (1)Roppongi is a special region in ~lbkyo where many discothetques exist (2)In order to go to some place, it is preferable to stay at a hotel near to the place (3)If something is preferable, the client tend to .....</Paragraph>
    <Paragraph position="13"> etc.</Paragraph>
    <Paragraph position="14"> A system which converses intelligently with human to make hotel reservation should have such knowledge and abilities of using it. However, a dialogue translation system has only to provide information to the human partic~ ipants who organize conversation intelligently.</Paragraph>
  </Section>
  <Section position="5" start_page="691" end_page="691" type="metho">
    <SectionTitle>
5 Active Participation of Speak-
</SectionTitle>
    <Paragraph position="0"> ers and Hearers What should be understood from texts is highly dependent on the intentions of actual writers and readers of texts, but r,either of them is available at the time of trauslation in textual translation.</Paragraph>
    <Paragraph position="1"> The same texts would be read by different readers with different intentions who would like to get different sorts of information from the translated texts.</Paragraph>
    <Paragraph position="2"> Readers of translated texts are often irritated because they cannot get necessary information for them. We found that translated texts are irritating not only because translations are awkward, but also because original texts tt,em.selves do not contain in/ormation which actual readers would like to get. Furthermore, evaluating translations produced by MT systems is difficult, because the evaluation highly depends on both what readers want to know and what source texts really contain. MT systems cannot produce good translations from bad source texts.</Paragraph>
    <Paragraph position="3"> However, the environments of dialogue translation systems, in which both actual writers and readers are available at the time of translation, are much better than tex. tual translation. The readers can ask questions directly  to the writers in order to get necessary inforn|ation, when they cannot get it from the translated messages or whctt they cannot understand the translations.</Paragraph>
    <Paragraph position="4"> Furthermore, the translation system can also pose questions to the writers (senders of messages) to clarify their intentions. We can expect an intelligent translation system to play a role of a coordinator of conversations by keeping track of exchanges of important in/srma~ion between dialogue participants (see Fig.a).</Paragraph>
    <Paragraph position="5"> \[EX 41 \[English participant\] In which region do you want to stay in Tokyo ? \[Japai, ese participant\] disuko~ni ikitai. (1 would like to go to disdotheqne) \[System's Question to the participant\] shitsumon-.</Paragraph>
    <Paragraph position="6"> ha anata-no kibou-suru hoteru-no basho desu ? (The question is 'in which resgion do you want to stay in Tokyo ?'. Would you specify the place which you prefer to stay ?) \[Japanese participant\] disuko-ni ehikai hoterudesu. (A hotel near to a discotheque) \[Translated reply to the English participant\] 1 prefer to stay a hotel near to a discotheque.</Paragraph>
    <Paragraph position="7"> Note also that what is important in dialogue translation is the exchange of information through translation but not translated texts obtained as the result. Transla.. tions are satisfactory when the participants achieve their goals, even if they are awkward. On the contrary, in textual translation, translated texts themselves are important and they should be natural and cleat' enough in all aspects, because different readers with different intention will read them and be interested in different aspects of informtional conteflts of same texts.</Paragraph>
  </Section>
class="xml-element"></Paper>