<?xml version="1.0" standalone="yes"?>
<Paper uid="W90-0103">
  <Title>A Connectionist Treatment of Grammar for Generation: Relying on Emergents</Title>
  <Section position="3" start_page="0" end_page="15" type="intro">
    <SectionTitle>
2 Parallel Syntax
</SectionTitle>
    <Paragraph position="0"> This section discusses two types of parallelism for syntax, proposes that a generator should have both of them, and sketches out the advantages of such an approach.</Paragraph>
    <Paragraph position="1"> Natural language generation research traditionally assumed that syntactic choices are made in a fixed (and generally top-down) order. Yet, for incremental generation at least, it is clear that a fixed order of decisions is not appropriate. This realization has led to generators which work on several parts of the input in parallel, simultaneously building several sub-trees. Recent work in this area includes (De Smedt 1990) and (Finkler &amp; Neumann 1989). I will refer to this type of parallelism as 'part-wise' parallelism.</Paragraph>
    <Paragraph position="2"> A second kind of parallelism involves using several constructions to generate even one part of the output. As far as I know, this 'within-part' parallelism has not been proposed in the generation literature. It has proven useful in linguistics. In Fillmore's Construction Grammar the syntactic  structure of sentences is accounted for in terms of 'superimposition' of constructions (Fillmore 1989b). It has also been used in psycholingnistics, where analysis of speech errors suggests that even normal speech is the result of competing 'plans' (Baars 1980). More specifically, (Stemberger 1985) suggested that human speakers can be modeled as having many 'phrase structure units' being 'partially activated' simultaneously. That is, many syntactic alternatives for expressing some piece of meaning are considered in parallel.</Paragraph>
    <Paragraph position="3"> I propose that a generator should exploit both part-wise and within-part parallelism.</Paragraph>
    <Paragraph position="4"> Parallel generation is a good idea for several reasons. 1.</Paragraph>
    <Paragraph position="5"> It has been observed that part-wise parallelism is a good way to improve the speed of response, especially for incremental generation. 2. Part-wise parallelism is also useful for handling dependencies. It is not always the case that one part can be processed without consideration of the way the surrounding utterance will turn out. If the various parts are generated in parallel then knowledge about the probable output for one part is available for consideration when building another part. This can lead to better quality. 3.</Paragraph>
    <Paragraph position="6"> Given the possibility of constraints among the various syntactic choices involved in building an utterance, there is the possibility that a 'first choice' will not work out when the larger context is considered. This suggests within-part parallelism, so that a generator has available alternative ways to realize some information. Given this it can find a set of choices satisfies all the dependencies, resulting in consistent and natural utterance. 4. If a generator is indeed to consider all the possible dependencies among choices, then parallelism becomes necessary to cope with the amount of computation necessary. 5. Parallelism is the natural way to generate if the input is very complex (Ward 1989a).</Paragraph>
  </Section>
class="xml-element"></Paper>