<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0102">
  <Title>Non-locality all the way through: Emergent Global Constraints in the Italian Morphological Lexicon</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Background
</SectionTitle>
    <Paragraph position="0"> Lazy learning methods such as the nearest neighbour algorithm (van den Bosch et al., 1996) or the analogy-based approach (Pirrelli and Federici, 1994; Pirrelli and Yvon, 1999) require full storage of supervised data, and make on-line use of them with no prior or posterior lexical structuring. This makes this class of algorithms flexible and efficient, but comparatively noise-sensitive and rather poor in simulating emergent learning phenomena. There is no explicit sense in which the system learns how to map new exemplars to already memorised ones, since the mapping function does not change through time and the only incremental pay-off lies in the growing quantity of information stored in the exemplar data-base.</Paragraph>
    <Paragraph position="1"> Decision tree algorithms (Quinlan, 1986), on the other hand, try to build the shortest hierarchical structure that best classifies the training data, using a greedy heuristics to select the most discriminative attributes near the root of the hierarchy. As heuristics are based on a locally optimal splitting of all training data, adding new training data may lead to a dramatic reorganisation of the hierarchy, and nothing is explicitly learned from having built a decision tree at a previous learning stage (Ling and Marinov, 1993).</Paragraph>
    <Paragraph position="2"> To tackle the issue of word structure more squarely, there has been a recent upsurge of interest in global paradigm-based constraints on morphology learning, as a way to minimise the range of inflectional or derivational endings heuristically inferred from raw training data (Goldsmith, 2001; Gaussier, 1999; Baroni, 2000). It should be noted, however, that global, linguistically-inspired constraints of this sort do not interact with morphology learning in any direct way. Rather, they are typically used as global criteria for optimal convergence on an existing repertoire of minimally redundant sets of paradigmatically related morphemes. Candidate morpheme-like units are acquired independently of paradigm-based constraints, solely on the basis of local heuristics.</Paragraph>
    <Paragraph position="3"> Once more, there is no clear sense in which global constraints form integral part of learning.</Paragraph>
    <Paragraph position="4"> Of late, considerable attention has been paid to aspects of emergent morphological structure and continuous compositionality in multi-layered perceptrons. Plaut et al. (1996) show how a neural network comes to be sensitive to degrees of compositionality on the basis of exposure to examples of inputs and outputs from a word-reading task.</Paragraph>
    <Paragraph position="5"> Systematic input-output pairs tend to establish a clear one-to-one correlation between parts of input and parts of output representations, thus developing strongly compositional analyses. By the same token, a network trained on inputs with graded morphological structure develops representations with corresponding degrees of compositionality (Rueckl and Raveh, 1999). It must be appreciated that most such approaches to incremental compostionality are task-oriented and highly supervised. Arguably, a better-motivated and more explanatory approach should be based on selforganisation of input tokens into morphologically natural classes and their time-bound specialisation as members of one such class, with no external supervision. Kohonen's Self-Organising Maps (SOMs) (Kohonen, 1995) simulate selforganisation by structuring input knowledge on a (generally) two-dimensional grid of neurons, whose activation values can be inspected by the researcher both instantaneously and through time.</Paragraph>
    <Paragraph position="6"> In the remainder of this paper we show that we can use SOMs to highlight interesting aspects of global morphological organisation in the learning of Italian conjugation, incrementally developed through local interactions between parallel processing neurons. null</Paragraph>
  </Section>
class="xml-element"></Paper>