<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-2119">
  <Title>Generalizing Automatically Generated Selectional Patterns</Title>
  <Section position="6" start_page="746" end_page="746" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> We \]tltve demonstrated how select.tonal p;~tl;erns ca.n lye attt;otn~tic;dly acquired from it corpus, ~md how selee tiond e,:)w~ragc gr~t(hlally it~ere~.tses with the size (,f the tra.ining eorl+us. We h~tve +dso domonst;r;tted that I'~)r it given corpus size eovcr++ge can I)e sig,tilicantly improved 1)y using 1,he corpus 1;o identify selectionally related ternts, and using these simila.rit.ies to generltlize the patterns tybserved in the training eorums. 'l'his is consisteut with other reeo,tt results using ,+eHtted l,eehniques \[2,9\].</Paragraph>
    <Paragraph position="1"> We believe th+tl; Lhese Lt:ehniques e+tn I)e ft,t'ther improved in several wa.ys. The exl)erin,ent.s rel)orl.e+l above ha+ve only get'~ra\]ized over t, ht, lit'st; (head) positioI, of t,he triples; we need to melrstu'o the eIl'&lt;~ct of gcncrldizhtg ow~r the al'gum&lt;mt l~OSh;ion as w&lt;ql. With btrger eorpor~ it, I~,~ty itlso be I&gt;asil)l{~ to use lirl+ger patterns, including in p~trtieular st,b.jeet-verl)-~d).ieet i)~tl;. terns, ;tnd thus reduce the confusion due to tre~tt, ing (li|t'et'e,lL words senses its eOlllltlOll eontexLs.</Paragraph>
  </Section>
class="xml-element"></Paper>