<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1021">
  <Title>Modern Natural Language Interfaces to Databases: Composing Statistical Parsing with Semantic Tractability</Title>
  <Section position="1" start_page="0" end_page="0" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> Natural Language Interfaces to Databases (NLIs) can benefit from the advances in statistical parsing over the last fifteen years or so. However, statistical parsers require training on a massive, labeled corpus, and manually creating such a corpus for each database is prohibitively expensive. To address this quandary, this paper reports on the PRECISE NLI, which uses a statistical parser as a &amp;quot;plug in&amp;quot;. The paper shows how a strong semantic model coupled with &amp;quot;light re-training&amp;quot; enables PRECISE to overcome parser errors, and correctly map from parsed questions to the corresponding SQL queries. We discuss the issues in using statistical parsers to build database-independent NLIs, and report on experimental results with the benchmark ATIS data set where PRECISE achieves 94% accuracy.</Paragraph>
  </Section>
class="xml-element"></Paper>