File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/abstr/00/p00-1058_abstr.xml
Size: 729 bytes
Last Modified: 2025-10-06 13:41:44
<?xml version="1.0" standalone="yes"?> <Paper uid="P00-1058"> <Title>Statistical parsing with an automatically-extracted tree adjoining grammar</Title> <Section position="2" start_page="0" end_page="0" type="abstr"> <SectionTitle> Abstract </SectionTitle> <Paragraph position="0"> We discuss the advantages of lexicalized tree-adjoining grammar as an alternative to lexicalized PCFG for statisticalparsing,describingthe induction of a probabilistic LTAG model from the Penn Treebank and evaluating its parsing performance. We #0Cnd that this induction method is an improvementover the EM-based method of #28Hwa, 1998#29, and that the induced model yields results comparable to lexicalized PCFG.</Paragraph> </Section> class="xml-element"></Paper>