File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/intro/90/c90-2003_intro.xml
Size: 1,133 bytes
Last Modified: 2025-10-06 14:04:51
<?xml version="1.0" standalone="yes"?> <Paper uid="C90-2003"> <Title>FINDING TRANSLATION EQUIVALENTS: AN APPLICATION OF GRAMMATICAL METAPHOR</Title> <Section position="2" start_page="0" end_page="0" type="intro"> <SectionTitle> Abstract </SectionTitle> <Paragraph position="0"> In this paper I describe how a significant class of cases that would involve (possibly complex) structural transfer in nmchine translation can be handled avoiding transfer. This is achieved by applying a semantic organization developed for monolingual text generation that is sufficiently abstract to remain invariant, within theoretically specifiable limits, across different languages. The further application of a mechanism motivated from within mono-lingual text generation, 'grammatical metaphor', then allows candidate appropriate translations to be isolated.</Paragraph> <Paragraph position="1"> The incorporation of these essentially monolingual mechanisms within the machine translation process promises to significantly improve translational capabilities; examples of this are presented for English and German.</Paragraph> </Section> class="xml-element"></Paper>