<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1034">
  <Title>Theory Refinement and Natural Language Learning Hervd Ddjean* Seminar fiir S1)rachwissenschaft</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Apl)lying Machine lx~'arning t('.chniques to Natural Language Processing is a booming domain of rus(:~ar('h. One of the reasons is the. (levelopment of cor1)ora with morl)ho-synta(:ti(: and syntacti(: mmotation (Marcus et al., 1993), (Sampson, 1995). One recent l)opular sul)task is the learning of non-re(:ursive Nouns Phrases (NP) (\]{amshaw and Mart:us, 1995), (~\['jong Kim Sang an(1 Vcenstra, 1999), (Mufioz et al., 1999), (Group, 1998), (Cardie and Pierce, 1999), (Buchholz el; al., 1999).</Paragraph>
    <Paragraph position="1"> When other learning tcchui(lues (symboli(: or statistical) are widely used in Natural Language Bern'hint, theory retlnelnent (Aliecker and Schmid, 199G), (Mooney, 1993) seems to be ignored (excel)t (Brunk and Pazzmfi, 1995)). Theory refinement consists of iml)roving an existing knowledge base so that it; better at:cords with data. No work using theory refinement apI)lied to tile grammar learning paradigm seems to have been develol)ed. We would like to point out in this article the adequacy between theory refinement and Natural Language Learning.</Paragraph>
    <Paragraph position="2"> To illustrate this claim, we present ALLiS (Architecture for Learning Linguistic Structures), a learning system which uses theory refinement in order to learn non-reeursive noun phrases (also called base norm t)hrases) and non-recursive verbal 1)hrases. We will show that this technique comliine(1 with the * This research is flmded be the TMll. network L('m'ning Coml)Ut;~tional (lrmnmars www. leg- www. uia. ac. be/lcg/ use of default vahms provides a good architecture to learn natural language structures.</Paragraph>
    <Paragraph position="3"> This article is organised as follows: Section 2 gives all overview of theory refinement. Section 3 CXl)Iains the advantage of combining default vahles and theory refinement to build a learning system. Section d des(:ril)es th('. genc'ral characteristics (if ALLiS, and Sc(:tion 5 explains the learning algorithm. The evaluation of ALLiS is described Section 6. The examples which illustrate this arti(:le corresl)ond to English NPs.</Paragraph>
  </Section>
class="xml-element"></Paper>