<?xml version="1.0" standalone="yes"?>
<Paper uid="W94-0101">
  <Title>Qualitative and Quantitative Models of Speech Translation</Title>
  <Section position="7" start_page="8" end_page="8" type="concl">
    <SectionTitle>
7. Conclusions
</SectionTitle>
    <Paragraph position="0"> Our qualitative and quantitative models have a similar overall structure and there are clear parallels between the factoring of logical constraints and statistical parameters, for example monolingual postulates and dependency parameters, bilingual postulates and translation parameters. The parallelism would have been closer if we had adopted ID/LP style rules (Gazdar et al. 1985) in the qualitative model. However, we argued in section 3 that our qualitative model suffered from lack of robustness, from having only the crudest means for choosing between competing hypotheses, and from being computationally intractable for large vocabularies. null The quantitative model is in a much better position to cope with these problems. It is less brittle because statistical associations have replaced constraints (featural, selectional, etc.) that must be satisfied exactly. The probabilistic models give us a systematic and well motivated way of ranking alternative hypotheses. Computationally, the quantitative model lets us escape from the undecidability of logic-based reasoning. Because this model is highly lexical, we can hope that the input words will allow effective pruning by limiting the number of search paths having significantly high probabilities. null We retained some of the basic assumptions about the structure of language when moving to the quantitative model. In particular, we preserved the notion of hierarchical phrase structure. Relations motivated by dependency grammar made it possible to do this without giving up sensitivity to lexical collocations which underpin simple statistical models like N-grams. The quantitative model also reduced overall complexity in terms of the sets of symbols used. In addition to words, it only required symbols for dependency relations, whereas the qualitative model required symbol sets for linguistic categories and features, and a set of word sense symbols. Despite their apparent importance to translation, the quantitative system can avoid the use of word sense symbols (and the problems of granularity they give rise to) by exploiting statistical associations between words in the target language to filter implicit sense choices.</Paragraph>
    <Paragraph position="1"> Finally, here is a summary of our reasons for combining statistical methods with dependency representations in our language and translation models: * inherent lexical sensitivity of dependency representations, facilitating parameter estimation; * quantitative preference based on probabilistic derivation and translation; * incremental and/or partial speeilication of tlw ~',~tltent of utterances, particularly useful in I, ranslatiou; * decomposition of complex utterances through rccursive linguistic structure.</Paragraph>
    <Paragraph position="2"> These factors suggest that dependency grammar will play an increasingly important role as language processing systems seek to combine both structural and colloeational information.</Paragraph>
  </Section>
class="xml-element"></Paper>