<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1034">
  <Title>MODULARITY IN A CONNECTIONIST MODEL MORPHOLOGY ACQUISITION</Title>
  <Section position="7" start_page="219" end_page="219" type="concl">
    <SectionTitle>
CONCLUSIONS
</SectionTitle>
    <Paragraph position="0"> Early work applying connectimfist networks to high-level cognitive tasks often seemed based on the assumption that a single network wouhl l)e al)le to handle a wide range of phenomena. Increasingly, however, the emphasis is moving in the direction of special-l)urpose modules for subtasks which may eontlict with each other if handled by the same hardware (aacobs et al., 1991). These apl)roaches bring eonnectionist models somewhat more in line with tile symbolic models which they seek to replace. In this paper I have shown how tile ability of simple recurrent networks to extract &amp;quot;structure in time&amp;quot; (Ehnan, 1990) is enhanced by built-in modularity which I)ermits the recurrent hidden-unit connections to develop in ways which are suitable for the root and inflection identification tasks. Not(., that this modularity does not amount to endowing the network with the distlnctiml 1)etween root and affix because both modules take the entire sequence of phones as input, and the modularity is the same when tile rule being learned is one for which there are 11o affixes at all (mutation, for examph!).</Paragraph>
    <Paragraph position="1"> Modular approaches, whether symbolic or connectionist, inevitably raise fllrther questions, however. The modularity in the pre-wired version of MCNAM, which is reminiscent of the traditional separation of lexical and grammatical knowledge in linguistic models, assumes that the division of &amp;quot;semantic&amp;quot; outlmt units into lexical and grammatical categories has already l)een made. The adaptive version partially addresses tills shortcoming, lint it is only etfective in cases where modularity 1)cuefits inflection identification. Furthermore, it is still based on the assumption that the output is divided initially into groups rel)resenting separate competing tasks. I am currently experimenting with related a(lal)tive approaches, as well as inethods involving weigl,t decay and weight pruning, which treat each output unit as a separate task.</Paragraph>
  </Section>
class="xml-element"></Paper>