<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1201">
  <Title>Two Statistical Parsing Models Applied to the Chinese Treebank</Title>
  <Section position="4" start_page="2" end_page="2" type="relat">
    <SectionTitle>
3 Experiments and Results
</SectionTitle>
    <Paragraph position="0"> The Chinese Treebank consists of 4185 sentences of Xinhua newswire text. We blindly separated this into training, devtest and test sets, with a roughly 80/10/10 split, putting files 001-270 (3484 sentences, 84,873 words) into the training set, 301-325 (353 sentences, 6776 words) into the development test set and reserving 271-300 (348 sentences, 7980 words) for testing. See Table 1 for results.</Paragraph>
    <Paragraph position="1"> In order to put the new Chinese Treebank results into context with the unmodified (English) parsing models, we present results on two test sets from the Wall Street Journal: WSJ-all, which is the complete Section 23 (the de facto standard test set for English parsing), and WSJ-small, which is the first 400 sentences of Section 23 and which is roughly comparable in size to the Chinese test set.</Paragraph>
    <Paragraph position="2"> Furthermore, when testing on WSJ-small, we trained on a subset of our English training data roughly equivalent in size to our Chinese training set (Sections 02 and 03 of the Penn Treebank); we have indicated models trained on all English training with &amp;quot;-all&amp;quot;, and models trained with the reduced English training set with &amp;quot;-small&amp;quot;. Therefore, by comparing the WSJ-small results with the Chinese results, one can reasonably gauge the performance gap between English parsing on the Penn Treebank and Chinese parsing on the Chinese Treebank.</Paragraph>
    <Paragraph position="3"> The reader will note that the modified BBN model does significantly poorer than (Chiang, 2000) on Chinese. While more investigation is required, we suspect part of the difference may be due to the fact that currently, the BBN model uses language-specific rules to guess part of speech tags for unknown words.</Paragraph>
  </Section>
class="xml-element"></Paper>