<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1067">
  <Title>Word Completion: A First Step Toward Target-Text Mediated IMT</Title>
  <Section position="3" start_page="0" end_page="394" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Machine translation is usually significantly inferior to human translation, and for most applications where high-quality results are needed it must be used in conjunction with a human translator. There are essentially three ways of organizing the process by which a person and a machine cooperate to produce a translation: prccdition, in which the person's contribution takes the form of a source-text analysis and occurs before the MT system is brought to bear; postedition, in which the translator simply edits the system's output; and interactive MT (IMT), which involves a dialog between person and machine. Of the three, IMT is the most ambitious and theoretically the most powerflfl. It has a potential advantage over postedition in that information imparted to the system may help it to avoid cascading errors that would later require much greater effort to correct; and it has a potential advantage over preedition in that knowledge of the machine's current state may be useful in reducing the number of analyses the human is required to provide.</Paragraph>
    <Paragraph position="1"> Existing approaches to IMT (Blanchon, 1994; Boitet, 1990; Brown and Nirenburg, 1990; Kay, 1973; Maruyama and Watanabe, 1990; Whitelock et al., 1986; Zajac, 1988) place the MT system in control of the translation process and for the most part limit the human's role to performing various source language disambiguations on deman&amp; Although this arrangement is appropriate for some applications, notably those in which the user's knowledge of tile target language may be limited, or where there are multiple target, languages, it is not well suited to tile needs of professional oi' other highly skilled translators. The lack of direct human control over the tinal target text (modulo postedition) is a serious drawback in this case, and it is not clear that, for a competent translator, disambiguat, ing a source text, is much easier than translating it. This conclusion is supported by the fact that true IMT is not, to our knowledge, used in most modern translator's support environments, eg (Eurolang, 1995; I,'rederking et al., 1993; IBM, 1995; Kugler et al., 1991; Nirenburg, 1992; ~li'ados, 1995). Such environments, when they incorporate MT at all, tend to do so wholesale, giving the user control over whether and when an MT component is invoked, as well as extensive postediting facilities for modifying its outtmt, but not the ability to intervene while it is operating.</Paragraph>
    <Paragraph position="2"> In our view, this state of affairs should not be taken as evidence that IMT for skilled translators is an inherently bad idea. We feel that there is an alternate approach which has the potential to avoid most of the problems with conventional IMT in this context,: use the target text as a medium of communication, and have the translator and MT system interact by making changes and extensions to it, with the translator's contributions serving as progressively informative constraints for the syste,n. This arrangement has the advantage of leaving the translator in full control of the translation process, of diverting his or her attention very little from the object of its natural focus, and of necessitating a minimum of interface paraphernalia beyond those of a word processor. It can in principle accomodate a wide range of MT proficien- null cies, frolil very high, in which the system inight be called ut)on to propose entire translations and Inoditly them in response to changes Inade by the translator; to very low, in which its chief contril)ution will be the reduction of typing labour.</Paragraph>
    <Paragraph position="3"> The aim of this paper ix to explore the feasibility of this target-tezt mediated style of IMT in one parti(:ularly simph; form: a word-(:onq)h',tion system which ai;temltts to fill in the sutlixes of target-text words from manually typed prefixes.t We describe a prototype completion system for English to l~Y=ench translation which is based on simple statistical MT techniques, att(t give mea-StlFenlents el: its performance ill terms of (;}laracters saved in a test cortms. The system has not yet been integrated with a word processor, st) we (;annot qltantify the anlollnt of a(:tual time and (;fl'ort it woul(t save a translator, t)nt it seems reasonable to expect this to lie faMy well correlated with total character savings.</Paragraph>
  </Section>
class="xml-element"></Paper>