<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1071">
  <Title>Evaluation of an Algorithm for the Recognition and Classification of Proper Names</Title>
  <Section position="5" start_page="421" end_page="422" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have described an IE system in which four classes of naming expressions (organisation, person, and location names and time expressions) are recognised and classified. The system was tested Oil 30 unseen Wall Street Journal texts and the results were analysed in terms of inajor system components and ditti~rent (:lasses of referring expression. null  Tables 3-6 an&lt;t Figure 2 enabh; us to make.</Paragraph>
    <Paragraph position="1"> the following observations: \]. Techniques relying on internal cwich;n(:c, only * e, xac:t word and phrase mat, thing, gral)hologic:al conventions, and t)arsing m'e not mlfficient, t;o re(:ognise and (:lassi(y organisal;ion names. It is clear l;hal; in order to have high recall for organisation names, we need 1;o l)e ;rifle to make good use, of exWxnal evidence as well, i.e. proper IlalSlO (;or(i'(;r(,,n(:(~ to, sol ul, ion and information fl'c&gt;m t;he sm'rounding (:onl;0,xI;.</Paragraph>
    <Paragraph position="2"> 2. On tim ol;her han(l, for person an(t lo(:ation names and time (;xprc',ssions, 1;echni(lueS relying soMy on inl;ernal evi&lt;h',nc(! &lt;1o t)e, rmil; us 1;o atl;ain high recall whilst maint, aining high precision. Thus, the &lt;:ontribution of difl'ercnt system coillt)OIlenl;s vm'ies fl'om one (:lass of t)rot)(;r name l;o anol;hcr.</Paragraph>
    <Paragraph position="3"> 3. I\[owever, giw',n that in a reasonable sample of business newswire text, 43 % of @c t)s'ot)er names are oigalfisal;ion names, it is (wi&lt;l(m(; that for a sysLcm I;o achieve high overall precision and re.(:all in the! name rec:ognil;ion and (:lassific:al;iol~ (;ask on this (;ext 1;yi)(~,, il; must; utilise not only inl, ernal evidence bul; also external (;viden(:c.</Paragraph>
    <Paragraph position="4"> More generally, I;wo (;Oll(:hlsiOSlS can Is(,, ds&amp;Wll. First, the results l)r(;s(mt(',d al)ove suggesl; t;hal; when a sysl;em fc)r t)rot)er IlalSl(! l'(;(;OgSlii;iosl an&lt;l/or c;lassificat;ion is evaluatc'd, mu('.h I)en(;fil: (:an t)e gained by analysing il; not only in t;erms of ovea'all recall and pre,&lt;:ision tigures, 1)ut; also in terms of sysl;(;Sll COSlll)OSlelll;S &amp;lid class&lt;',s of IlalIICS. S(:(;OSI(I~ a heterogeneous approach l;o l;he r(',cognit;ion an(l classifi(:ation of t)l.'Ot)c'r names in n(,,wswir(; |;o, xl; such as describ(xt here is at)t)r&lt;)priat;(,' sin&lt;:e il; provides me, chanisms thai; can utilis(; the variety of internal and external evidence which is available and which needs t,o b(; taken inl;o a(:(;ounl;.</Paragraph>
  </Section>
class="xml-element"></Paper>