File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/03/w03-1024_concl.xml
Size: 898 bytes
Last Modified: 2025-10-06 13:53:48
<?xml version="1.0" standalone="yes"?> <Paper uid="W03-1024"> <Title>Japanese Zero Pronoun Resolution based on Ranking Rules and Machine Learning</Title> <Section position="6" start_page="0" end_page="0" type="concl"> <SectionTitle> 5 Conclusions </SectionTitle> <Paragraph position="0"> In order to make Japanese zero pronoun resolution more reliable, we have to maintain complicated heuristic rules or prepare a large amount of training data. In order to alleviate this problem, we combined simple lexicographical orderings and SVMs.</Paragraph> <Paragraph position="1"> It turned out that a simple lexicographical ordering performed better than SVM, but their combination gave even better performance. By examining feature weights, we found that features for complex sentences are important in zero pronoun resolution. We confirmed this by feature elimination.</Paragraph> </Section> class="xml-element"></Paper>