<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-1055">
  <Title>Semantic Role Labeling of Nominalized Predicates in Chinese</Title>
  <Section position="2" start_page="0" end_page="431" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Detecting and classifying the arguments of predicates has been an active area of research in recent years, driven by the availability of large-scale semantically annotated corpora such as the FrameNet (Baker et al., 1998) and the Propbank (Palmer et al., 2005). It is generally formulated as a semantic role labeling (SRL) task, where each argument of the predicate is assigned a label that represents the semantic role it plays with regard to its predicate (Gildea and Jurafsky, 2002; Hacioglu et al., 2003; Pradhan et al., 2004b; Xue and Palmer, 2004; Toutanova et al., 2005; Koomen et al., 2005). It has been the shared task for the CoNLL competition for two consecutive years (Carreras and M`arquez, 2004b; Carreras and M`arquez, 2005). This line of research has also expanded from English to other languages (Sun and Jurafsky, 2004; Xue and Palmer, 2005). So far, however, most of the research efforts have focused on analyzing the predicate-argument structure of verbs, largely due to absence of annotated data for other predicate types. In this paper, we report SRL experiments performed on nominalized predicates in Chinese, taking advantage of a newly completed corpus, the Chinese Nombank (Xue, 2006), which we describe in greater detail in Section 2. The rest of the paper is organized as follows. Section 3 describes the architecture of our system as well as the features we used in our experiments. In Section 4 we describe the experimental setups and report our experimental results. We first present experiments that use hand-crafted parses as input, providing a measurement of how well the Nombank annotation can be bootstrapped from the syntactic structure in the treebank. We then describe a more realistic experimental setup in which an automatic parser is first used to parse unsegmented raw  text and its output is then fed into our SRL system.</Paragraph>
    <Paragraph position="1"> We also discuss whether verb data can be used to improve the SRL accuracy of nominalized predicates.</Paragraph>
    <Paragraph position="2"> Finally we describe a preliminary experiment that uses reranking techniques to improve the SRL accuracy on hand-crafted parses. Section 5 attempts to put our results in perspective in the context of related work. Section 6 concludes our paper.</Paragraph>
  </Section>
class="xml-element"></Paper>