File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/evalu/93/h93-1049_evalu.xml
Size: 819 bytes
Last Modified: 2025-10-06 14:00:11
<?xml version="1.0" standalone="yes"?> <Paper uid="H93-1049"> <Title>HYPOTHESIZING UNTAGGED TEXT WORD ASSOCIATION FROM</Title> <Section position="11" start_page="251" end_page="251" type="evalu"> <SectionTitle> 8. CONCLUSION </SectionTitle> <Paragraph position="0"> Our method achieved fully automatic hypothesis of word associations, starting from untagged text and generalizing to unobserved word associations. As a result of human review 87% of the hypotheses were judged to be reasonable. Because the technique considers low frequency cases, most of the data was used in making generalizations.</Paragraph> <Paragraph position="1"> It remains to be determined how well this method will work for English, but with appropriate finite state patterns, similar results may be achieved.</Paragraph> </Section> class="xml-element"></Paper>