<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-2005">
  <Title>A Multi-Path Architecture for Machine Translation of English Text into American Sign Language Animation</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> The translation of English text into American Sign Language (ASL) animation tests the limits of traditional MT architectural designs.</Paragraph>
    <Paragraph position="1"> A new semantic representation is proposed that uses virtual reality 3D scene modeling software to produce spatially complex ASL phenomena called &amp;quot;classifier predicates.&amp;quot; The model acts as an interlingua within a new multi-pathway MT architecture design that also incorporates transfer and direct approaches into a single system.</Paragraph>
  </Section>
class="xml-element"></Paper>