<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0614">
  <Title>Intentional Context in Situated Natural Language Learning</Title>
  <Section position="2" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Natural language interfaces designed for situationally embedded domains (e.g.</Paragraph>
    <Paragraph position="1"> cars, videogames) must incorporate knowledge about the users' context to address the many ambiguities of situated language use. We introduce a model of situated language acquisition that operates in two phases. First, intentional context is represented and inferred from user actions using probabilistic context free grammars.</Paragraph>
    <Paragraph position="2"> Then, utterances are mapped onto this representation in a noisy channel framework. The acquisition model is trained on unconstrained speech collected from subjects playing an interactive game, and tested on an understanding task.</Paragraph>
  </Section>
class="xml-element"></Paper>