<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0808">
  <Title>A hybrid approach to align sentences and words in English-Hindi parallel corpora</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> In this paper we describe an alignment system that aligns English-Hindi texts at the sentence and word level in parallel corpora. We describe a simple sentence length approach to sentence alignment and a hybrid, multi-feature approach to perform word alignment.</Paragraph>
    <Paragraph position="1"> We use regression techniques in order to learn parameters which characterise the relationship between the lengths of two sentences in parallel text. We use a multi-feature approach with dictionary lookup as a primary technique and other methods such as local word grouping, transliteration similarity (edit-distance) and a nearest aligned neighbours approach to deal with many-to-many word alignment.</Paragraph>
    <Paragraph position="2"> Our experiments are based on the EMILLE (Enabling Minority Language Engineering) corpus. We obtained 99.09% accuracy for many-to-many sentence alignment and 77% precision and 67.79% recall for many-to-many word alignment.</Paragraph>
  </Section>
class="xml-element"></Paper>