File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/88/p88-1019_concl.xml
Size: 2,052 bytes
Last Modified: 2025-10-06 13:56:22
<?xml version="1.0" standalone="yes"?> <Paper uid="P88-1019"> <Title>EXPERIENCES WITH AN ON-LINE TRANSLATING DIALOGUE SYSTEM</Title> <Section position="8" start_page="159" end_page="160" type="concl"> <SectionTitle> CONCLUSIONS </SectionTitle> <Paragraph position="0"> There are a number of things to be learnt from this experiment, even if it was not in fact set up to elicit information of this kind. Clearly, typing errors are a huge source of problems, so an environment which minimizes these is highly desirable. Two obvious features of such an environment are fast screen echo, and delete and back-space keys which work in a predictable manner in relation to what is seen on the screen. For the correction of typing errors, the system should have a spelling- null check function which works word-by-word as users are typing in. The main reasons for syntax errors are ellipsis and unknown words. Therefore, the system should have a rapid syntax-check function which can work before transmission or translation and can indicate to users that there is a syntax error so that users can edit the input sentence or reenter the correct sentence. These are in themselves not new ideas, of course (e.g. Kay 1980 and others).</Paragraph> <Paragraph position="1"> Conventions for citing forms not to be translaw, d, especially in metadialogue, must be developed, and the Machine Translation system must be sensitive to these. The system must be 'tuned' in other ways to make translations appropriate to conversation, in particular in the translation of conversational fillers like I see and wakarimashita.</Paragraph> <Paragraph position="2"> Finally, it seems to be desirable that users be trained briefly, not only to learn these conventions, but also so that they understand the limits of the system, and the kind of errors that get produced, especially since these are rather different from the errors occasionally produced by human translators or people conversing in a foreign language that they know only partially.</Paragraph> </Section> class="xml-element"></Paper>