<?xml version="1.0" standalone="yes"?>
<Paper uid="W02-1022">
  <Title>Bootstrapping Lexical Choice via Multiple-Sequence Alignment</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> An important component of any generation system is the mapping dictionary, a lexicon  ofelementarysemanticexpressionsandcorresponding natural language realizations. Typically, labor-intensive knowledge-based methods are used to construct the dictionary. We instead propose to acquire it automatically via a novel multiple-pass algorithm employing multiple-sequence alignment, a technique commonly used in bioinformatics. Crucially, our method leverages latent information contained in multi-parallel corpora  |datasets that supply several verbalizations of the corresponding semantics rather than just one.</Paragraph>
    <Paragraph position="1"> We used our techniques to generate natural language versions of computer-generated mathematical proofs, with good results on both a per-component and overall-output basis. For example, in evaluations involving a dozen human judges, our system produced output whose readability and faithfulnesstothesemanticinputrivaledthatof null a traditional generation system.</Paragraph>
  </Section>
class="xml-element"></Paper>