<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1075">
  <Title>Growing Semantic Grammars</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The mapping between words and semantics, be it in the form of a semantic grammar, t or of a set of rules that transform syntax trees onto, say, a frame-slot structure, is one of the major bottlenecks in the development of natural language understanding (NLU) systems. A parser will work for any domain but the semantic mapping is domain-dependent. Even after the domain model has been established, the daunting task of trying to come up with all the possible surface forms by which each concept can 1 Semantic grammars are grammars whose non-terminals correspond to semantic concepts (e.g., \[greeting\] or \[suggest.time\] ) rather than to syntactic constituents (such as Verb or WounPhrase). They have the advantage that the semantics of a sentence can be directly read off its parse tree, and the disadvantage that a new grammar must be developed for each domain.</Paragraph>
    <Paragraph position="1"> be expressed, still lies ahead. Writing such mappings takes in the order of years, can only be performed by qualified humans (usually computational linguists) and yet the final result is often fragile and non-adaptive.</Paragraph>
    <Paragraph position="2"> Following a radically different philosophy, we propose rapid (in the order of days) deployment of NLU modules for new domains with on-need basis learning: let the semantic grammar grow automatically when and where it is needed.</Paragraph>
  </Section>
class="xml-element"></Paper>