<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1099">
  <Title>A TOOL FOR COLLECTING DOMAIN DEPENDENT SORTAL CONSTRAINTS FROM CORPORA</Title>
  <Section position="9" start_page="602" end_page="602" type="concl">
    <SectionTitle>
7 CONCLUSION
</SectionTitle>
    <Paragraph position="0"> This first evahmtion of our tool in the ATIS domain shows tlmt the acquisition of sorts from a corpus can be partially automated, reducing drastically the time the linguistic dedicates to this task (the precision converges in few editing iteration).</Paragraph>
    <Paragraph position="1"> In addition to this, the possibility of a systematic examination for all predicates with crosschecldng tools such as sentence visualisation and funetor browing helps the linguist to establish strict aquisition methods for the knowledge base in new donlgins. null In addition to this, the tool can also lie used to improve an existing knowledge /)ase. For example, the study of the ineoml)atilde rules d,,ring this \[i,'st evaluatio,l helped us {.o discover new rules that will increase the coverage of (iemini in the ATIS system.</Paragraph>
  </Section>
class="xml-element"></Paper>