<?xml version="1.0" standalone="yes"?>
<Paper uid="W01-0712">
  <Title>Learning Computational Grammars</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> This paper reports on the still preliminary, but already satisfying results of the LEARNING COM-PUTATIONAL GRAMMARS (LCG) project, a postdoc network devoted to studying the application of machine learning techniques to grammars suitable for computational use. The member institutes are listed with the authors and also included ISSCO at the University of Geneva. We were impressed by early experiments applying learning to natural language, but dissatisfied with the concentration on a few techniques from the very rich area of machine learning. We were interested in  a more systematic survey to understand the relevance of many factors to the success of learning, esp. the availability of annotated data, the kind of dependencies in the data, and the availability of knowledge bases (grammars). We focused on syntax, esp. noun phrase (NP) syntax from the beginning. The industrial partner, Xerox, focused on more immediate applications (Cancedda and Samuelsson, 2000).</Paragraph>
    <Paragraph position="1"> The network was focused not only by its scientific goal, the application and evaluation of machine-learning techniques as used to learn natural language syntax, and by the subarea of syntax chosen, NP syntax, but also by the use of shared training and test material, in this case material drawn from the Penn Treebank. Finally, we were curious about the possibility of combining different techniques, including those from statistical and symbolic machine learning. The network members played an important role in the organisation of three open workshops in which several external groups participated, sharing data and test materials.</Paragraph>
  </Section>
class="xml-element"></Paper>