<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1317">
  <Title>Automated Construction of Database Interfaces: Integrating Statistical and Relational Learning for Semantic Parsing</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> We use the term semantic parsing to refer to the process of mapping a natural language sentence to a structured meaning representation. One interesting application of semantic parsing is building natural language interfaces for online databases. The need for such applications is growing since when information is delivered through the Internet, most users do not know the underlying database access language. An example of such an interface that we have developed is shown in Figure 1.</Paragraph>
    <Paragraph position="1"> Traditional (rationalist) approaches to constructing database interfaces require an expert to hand-craft an appropriate semantic parser (Woods, 1970; Hendrix et al., 1978).</Paragraph>
    <Paragraph position="2"> However, such hand-crafted parsers are time consllming to develop and suffer from problems with robustness and incompleteness even for domain specific applications. Nevertheless, very little research in empirical NLP has explored the task of automatically acquiring such interfaces from annotated training examples. The only exceptions of which we are aware axe a statistical approach to mapping airline-information queries into SQL presented in (Miller et al., 1996), a probabilistic decision-tree method for the same task described in (Kuhn and De Mori, 1995), and an approach using relational learning (a.k.a.</Paragraph>
    <Paragraph position="3"> inductive logic programming, ILP) to learn a logic-based semantic parser described in (Zelle and Mooney, 1996).</Paragraph>
    <Paragraph position="4"> The existing empirical systems for this task employ either a purely logical or purely statistical approach. The former uses a deterministic parser, which can suffer from some of the same robustness problems as rationalist methods. The latter constructs a probabilistic grammar, which requires supplying a sytactic parse tree as well as a semantic representation for each training sentence, and requires hand-crafting a small set of contextual features on which to condition the parameters of the model. Combining relational and statistical approaches can overcome the need to supply parse-trees and hand-crafted features while retaining the robustness of statistical parsing. The current work is based on the CHILL logic-based parser-acquisition framework (Zelle and Mooney, 1996), retaining access to the complete parse state for making decisions, but building a probabilistic relational model that allows for statistical parsing- null</Paragraph>
  </Section>
class="xml-element"></Paper>