<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2419">
  <Title>Semantic Role Labeling using Maximum Entropy Model</Title>
  <Section position="5" start_page="2" end_page="3" type="evalu">
    <SectionTitle>
4 Experiments
</SectionTitle>
    <Paragraph position="0"> To test the proposed method, we have experimented on CoNLL-2004 datasets. For our experiments, we use the Zhang le's MaxEnt toolkit  , and the L-BFGS parameter estimation algorithm with Gaussian Prior smoothing (Chen, 1999). The results on the test set are shown in Table 3, and Table 4 shows the overall results when the model is tested on the training set, the development set, and the test set.</Paragraph>
    <Paragraph position="1"> From these experimental results, we can find that the proposed model has relatively high performance on the labels related to A0 and A1, while it has relatively low performance on the other labels. This may be caused by following two reasons. Firstly, the instances of A0 or A1 are provided enough for accurate semantic role labeling. Secondly, the thematic roles of A0 and A1 are more clear than other core semantic roles. For example, agent is labeled as mainly A0 while benefactive can be labeled as A2 or A3. Therefore, the maximum entropy model can  ing set, the development set, and the test set get a good generalize performance in case of A0 or A1, but can't generalize well in other cases.</Paragraph>
  </Section>
class="xml-element"></Paper>