<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1011">
  <Title>Loosely Tree-Based Alignment for Machine Translation</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Systems for automatic translation between languages have been divided into transfer-based approaches, which rely on interpreting the source string into an abstract semantic representation from which text is generated in the target language, and statistical approaches, pioneered by Brown et al. (1990), which estimate parameters for a model of word-to-word correspondences and word re-orderings directly from large corpora of parallel bilingual text. Only recently have hybrid approaches begun to emerge, which apply probabilistic models to a structured representation of the source text. Wu (1997) showed that restricting word-level alignments between sentence pairs to observe syntactic bracketing constraints significantly reduces the complexity of the alignment problem and allows a polynomial-time solution.</Paragraph>
    <Paragraph position="1"> Alshawi et al. (2000) also induce parallel tree structures from unbracketed parallel text, modeling the generation of each node's children with a finite-state transducer. Yamada and Knight (2001) present an algorithm for estimating probabilistic parameters for a similar model which represents translation as a sequence of re-ordering operations over children of nodes in a syntactic tree, using automatic parser output for the initial tree structures. The use of explicit syntactic information for the target language in this model has led to excellent translation results (Yamada and Knight, 2002), and raises the prospect of training a statistical system using syntactic information for both sides of the parallel corpus.</Paragraph>
    <Paragraph position="2"> Tree-to-tree alignment techniques such as probabilistic tree substitution grammars (HajiVc et al., 2002) can be trained on parse trees from parallel treebanks. However, real bitexts generally do not exhibit parse-tree isomorphism, whether because of systematic differences between how languages express a concept syntactically (Dorr, 1994), or simply because of relatively free translations in the training material.</Paragraph>
    <Paragraph position="3"> In this paper, we introduce &amp;quot;loosely&amp;quot; tree-based alignment techniques to address this problem. We present analogous extensions for both tree-to-string and tree-to-tree models that allow alignments not obeying the constraints of the original syntactic tree (or tree pair), although such alignments are dispreferred because they incur a cost in probability. This is achieved by introducing a clone operation, which copies an entire subtree of the source language syntactic structure, moving it anywhere in the target language sentence. Careful parameterization of the probability model allows it to be estimated at no additional cost in computational complexity. We expect our relatively unconstrained clone operation to allow for various types of structural divergence by providing a sort of hybrid between tree-based and unstructured, IBM-style models.</Paragraph>
    <Paragraph position="4"> We first present the tree-to-string model, followed by the tree-to-tree model, before moving on to alignment results for a parallel syntactically annotated Korean-English corpus, measured in terms of alignment perplexities on held-out test data, and agreement with human-annotated word-level alignments.</Paragraph>
  </Section>
class="xml-element"></Paper>