<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2805">
  <Title>Scalable Construction-Based Parsing and Semantic Analysis</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> As described by (Chang et al., 2002), the semantic and pragmatic insights provided by cognitive linguistics must be incorporated into a language understanding system before deep understanding can take place. Embodied Construction Grammar (ECG) (Chang et al., 2002), (Bergen and Chang, 2002) is a rigorous, formalism incorporating such insight. It provides formal mechanism for describing cognitive primitives like linguistic constructions (Goldberg, 1995), image schemas (Lakoff, 1987), frames (Fillmore, 1982), and mental spaces (Fauconnier and Turner, 2002), as well as cross-domain mappings.</Paragraph>
    <Paragraph position="1"> From a system-building point of view, however, the importance of ECG lies in its scalability. Within its unification-based framework, constructions, frames and mental spaces are combined compositionally, yielding a network of entwined semantic and pragmatic structures representing the overall interpretation. This makes it possible for ECG to scale to much more complex linguistic data that previous formalisms would allow.</Paragraph>
    <Paragraph position="2"> The work described in this paper builds on this system-building perspective since it is a system that leverages the ECG formalism to perform deep, scalable construction-based parsing and semantic analysis. It incorporates an implementation of ECG's semantic and constructional primitives as well as integrating scalable language analysis algorithms like level-based parsing (Abney, 1996).</Paragraph>
    <Paragraph position="3"> This system is called the constructional analyzer and it fits into a larger framework for scalable, simulation-based language understanding.</Paragraph>
    <Paragraph position="4"> In a simulation-based model of language understanding, interpretation of an utterance is split into two phases: analysis and enactment. Analysis is the process of mapping forms to context-independent meanings, providing the input parameters for enactment. Enactment uses an active, simulation-based model to generate context-specific inference. This process-level separation of analysis and inference provides further scalability.</Paragraph>
    <Paragraph position="5"> The next three sections describe the ECG formalism, simulation-based understanding and partial parsing. Then the constructional analyzer is described along with an example. The paper closes with a description of a language analysis task requiring the deep semantic representation afforded by the constructional analyzer.</Paragraph>
  </Section>
class="xml-element"></Paper>