<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-1032">
  <Title>Grammatical Machine Translation</Title>
  <Section position="2" start_page="0" end_page="248" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Recent approaches to statistical machine translation (SMT) piggyback on the central concepts of phrase-based SMT (Och et al., 1999; Koehn et al., 2003) and at the same time attempt to improve some of its shortcomings by incorporating syntactic knowledge in the translation process. Phrase-based translation with multi-word units excels at modeling local ordering and short idiomatic expressions, however, it lacks a mechanism to learn long-distance dependencies and is unable to generalize to unseen phrases that share non-overt linguistic information. Publicly available statistical parsers can provide the syntactic information that is necessary for linguistic generalizations and for the resolution of non-local dependencies. This information source is deployed in recent work either for pre-ordering source sentences before they are input to to a phrase-based system (Xia and McCord, 2004; Collins et al., 2005), or for re-ordering the output of translation models by statistical ordering models that access linguistic information on dependencies and part-of-speech (Lin, 2004; Ding and Palmer, 2005; Quirk et al., 2005)1.</Paragraph>
    <Paragraph position="1"> While these approaches deploy dependency-style grammars for parsing source and/or target text, a utilization of grammar-based generation on the output of translation models has not yet been attempted in dependency-based SMT. Instead, simple target language realization models that can easily be trained to reflect the ordering of the reference translations in the training corpus are preferred. The advantage of such models over grammar-based generation seems to be supported, for example, by Quirk et al.'s (2005) improvements over phrase-based SMT as well as over an SMT system that deploys a grammar-based generator (Menezes and Richardson, 2001) on n-gram based automatic evaluation scores (Papineni et al., 2001; Doddington, 2002). Another data point, however, is given by Charniak et al. (2003) who show that parsing-based language modeling can improve grammaticality of translations, even if these improvements are not recorded under n-gram based evaluation measures.</Paragraph>
    <Paragraph position="2">  In this paper we would like to step away from n-gram based automatic evaluation scores for a moment, and investigate the possible contributions of incorporating a grammar-based generator into a dependency-based SMT system. We present a dependency-based SMT model that integrates the idea of multi-word translation units from phrase-based SMT into a transfer system for dependency structure snippets. The statistical components of our system are modeled on the phrase-based system of Koehn et al. (2003), and component weights are adjusted by minimum error rate training (Och, 2003). In contrast to phrase-based SMT and to the above cited dependency-based SMT approaches, our system feeds dependency-structure snippets into a grammar-based generator, and determines target language ordering by applying n-gram and distortion models after grammar-based generation. The goal of this ordering model is thus not foremost to reflect the ordering of the reference translations, but to improve the grammaticality of translations.</Paragraph>
    <Paragraph position="3"> Since our system uses standard SMT techniques to learn about correct lexical choice and idiomatic expressions, it allows us to investigate the contribution of grammar-based generation to dependency-based SMT2. In an experimental evaluation on the test-set that was used in Koehn et al. (2003) we show that for examples that are in coverage of the grammar-based system, we can achieve state-of-the-art quality on n-gram based evaluation measures. To discern the factors of grammaticality and translational adequacy, we conducted a manual evaluation on 500 in-coverage and 500 out-of-coverage examples. This showed that an incorporation of a grammar-based generator into an SMT framework provides improved grammaticality over phrase-based SMT on in-coverage examples. Since in our system it is determinable whether an example is in-coverage, this opens the possibility for a hybrid system that achieves improved grammaticality at state-of-the-art translation quality.</Paragraph>
    <Paragraph position="4"> 2A comparison of the approaches of Quirk et al. (2005) and Menezes and Richardson (2001) with respect to ordering models is difficult because they differ from each other in their statistical and dependency-tree alignment models.</Paragraph>
  </Section>
class="xml-element"></Paper>