<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1045">
  <Title>Pronominalization revisited*</Title>
  <Section position="6" start_page="310" end_page="311" type="evalu">
    <SectionTitle>
5 Evaluation
</SectionTitle>
    <Paragraph position="0"> A comparison of the t)erforlnance of our algorithln with 1,he annotated MUS1.; corlms and McCoy and Strube's newspatmr corlms is given in  for the algorithm gnome-np without cm\])loying the rel)etith)n blocking rule and without; a line-grained discourse segmentation. Layout scglllell{;s Wel'e llse(l for the MUSE COl'l)llS. Beeallse l/he munl)er of annotal;e(l seglnent OllSe\[;s Jill' the newsl)aper corpus is not easy to r('-estat)lish, wc giv(; here two figures fol&amp;quot; this eori)us: tirst without any segment, ons('t signalling (lower 1)ound), and second with the assulnt)l;ion that 15 short-distance definite (tcscriptions mark segment ons&lt;%s. The tigures include locally-herald l/re nouns to yield J)(;tter cOlnl)arability wil;h McCoy and Sl;rul)e. '.\[lic, figur(,'s in l,hc, (:ohmms 'gnomenil' represc, nl; I;\]lose NPs whose form is l)re(li(',led correctly 1)y 1;hi; new algoril;hm when evaluatc(l against l;h('~ a\]moi;at,(~(l corpora.</Paragraph>
    <Paragraph position="1"> The figures in T~d)le 1 show that our algorithm performs very well in both domains, even without using a tiner discourse Seglnenration such as telnt)ol'al structure. Moreover, it; pertBrms better on McCoy and Stl'ul)e's corpus than their own algorithm, which successfldly predicted the choice between realization by pronoml and realization by detinite description in 84.7% of all eases. The disagreements oc('ur tirsl; tbr long distance t)rol~ouns (in our terlilino\]ogy: prollOtlllS lIlore than one clause distanI;) and, second, ill hmger tel'trent chains with well established focus. For the latter, whereas gnome-np wouhl always suggest a tn'OlmUn, the real discourse swaps betweeli pronoun mid deftnile description. Thus a finer segmentation or a repetition blocking rule could still improve the result fllrther.</Paragraph>
  </Section>
class="xml-element"></Paper>