<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-1303">
  <Title>Putting Meaning into Grammar Learning</Title>
  <Section position="2" start_page="17" end_page="18" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> What role does meaning play in the acquisition of grammar? Computational approaches to grammar learning have tended to exclude semantic information entirely, or else relegate it to lexical representations. Starting with Gold's (1967) influential early work on language identifiability in the limit and continuing with work in the formalist learnability paradigm, grammar learning has been equated with syntax learning, with the target of learning consisting of relatively abstract structures that govern the combination of symbolic linguistic units. Statistical, corpus-based efforts have likewise restricted their attention to inducing syntactic patterns, though in part due to more practical considerations, such as the lack of large-scale semantically tagged corpora.</Paragraph>
    <Paragraph position="1"> But a variety of cognitive, linguistic and developmental considerations suggest that meaning plays a central role in the acquisition of linguistic units at all levels. We start with the proposition that language use should drive language learning -- that is, the learner's goal is to improve its ability to communicate, via comprehension and production. Cognitive and constructional approaches to grammar assume that the basic unit of linguistic knowledge needed to support language use consists of pairings of form and meaning, or constructions (Langacker, 1987; Goldberg, 1995; Fillmore and Kay, 1999).</Paragraph>
    <Paragraph position="2"> Moreover, by the time children make the leap from single words to complex combinations, they have amassed considerable conceptual knowledge, including familiarity with a wide variety of entities and events and sophisticated pragmatic skills (such as using joint attention to infer communicative intentions (Tomasello, 1995) and subtle lexical distinctions (Bloom, 2000)). The developmental evidence thus suggests that the input to grammar learning may in principle include not just surface strings but also meaningful situation descriptions with rich semantic and pragmatic information.</Paragraph>
    <Paragraph position="3"> This paper formalizes the grammar learning problem in line with the observations above, taking seriously the ideas that the target of learning, for both lexical items and larger phrasal and clausal units, is a bipolar structure in which meaning is on par with form, and that meaningful language use drives language learning. The resulting core computational problem can be seen as a restricted type of relational learning. In particular, a key step of the learning task can be cast as learning relational correspondences, that is, associations between form relations (typically word order) and meaning relations (typically role-filler bindings). Such correlations are essential for capturing complex multi-unit constructions, both lexically specific constructions and more general grammatical constructions.</Paragraph>
    <Paragraph position="4"> The remainder of the paper is structured as follows. Section 2 states the learning task and provides an overview of the model and its assumptions. We then present algorithms for inducing structured mappings, based on either specific input examples or the current set of constructions (Section 3), and describe how these are evaluated using criteria based on minimum description length (Rissanen, 1978). Initial results from applying the learning algorithms to a small corpus of child-directed utterances demonstrate the viability of the approach (Section 4). We conclude with a discussion of the broader implications of this approach for language learning and use.</Paragraph>
  </Section>
class="xml-element"></Paper>