<?xml version="1.0" standalone="yes"?>
<Paper uid="P00-1065">
  <Title>Automatic Labeling of Semantic Roles</Title>
  <Section position="7" start_page="8" end_page="8" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> Our preliminary system is able to automatically label semantic roles with fairly high accuracy, indicating promise for applications in various natural language tasks. Lexical statistics computedon constituentheadwords were found to be the most important of the features used. While lexical statistics are quite accurate on the data covered by observations in the training set, the sparsity of the data when conditioned on lexical items meant that combining features was the key to high over-all performance. While the combined system was far more accurate than any feature Type of Overlap Identi#0Ced Constituents Number Exactly Matching Boundaries 66#25 5421 Identi#0Ced constituent entirely within true frame element 8 663 True frame elemententirely within identi#0Ced constituent 7 599 Partial overlap 0 26 No match to true frame element 13 972 Table 6: Results on Identifying Frame Elements #28FEs#29, including partial matches. Results obtained using P#28fejpath#29 with threshold at .5. A total of 7681 constituents were identi#0Ced as FEs, 8167 FEs were present in hand annotations, of which matching parse constituents were present for 7053 #2886#25#29.</Paragraph>
    <Paragraph position="1"> taken alone, the speci#0Cc method of combination used was less important.</Paragraph>
    <Paragraph position="2"> We plan to continue this work byintegrating semantic role identi#0Ccation with parsing, by bootstrapping the system on larger, and more representative, amounts of data, and by attempting to generalize from the set of predicates chosen by FrameNet for annotation to general text.</Paragraph>
  </Section>
class="xml-element"></Paper>