<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1035">
  <Title>Aspects of Pattern-matching in Data-Oriented Parsing</Title>
  <Section position="12" start_page="240" end_page="241" type="ackno">
    <SectionTitle>
10 Conclusions
</SectionTitle>
    <Paragraph position="0"> Even though l)()l'\] exhil)its outstanding parsing 1)eh~vior, the et|iciency of the model is rathe, r problematic. The introduction of multit fie deriwd;ions causes a considerable amount of computational overhead. Neither is it clear how the concept of multiple deriwd;ions translal;es to a t)sycholinguistic context: there is no proof thai; lmlguage users consider (titf'(;rcnt inst~mtiations of th(; same parse, whmt deciding on the correct anMysis for a given sentence.</Paragraph>
    <Paragraph position="1"> A 1)M;tcrn-m~t:chil~g schcnm w~s 1)rcsenLcd that tried to dis~mfl)iguate parse forests by trying to maximize the size of the sul)strnctures that can 1)e retrie, ved from inoanory. This straightforward memory-based intert)rctation yields sut)-standm'd parsing accuracy. But the (:oml)ination of common-sense l)robal)ilities nnd enhanced context-sensitivity provides a workM)le t)arse forest disambiguator, indicating that language users might exert a COml)lex corot)libation of memory-based recollection techniques and stored statistical data to analyze utterances. null</Paragraph>
  </Section>
class="xml-element"></Paper>