<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1186">
  <Title>Semantic Role Labeling Using Dependency Trees</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In semantic role labeling (SRL) the goal is to group sequences of words together and classify them by using semantic labels. For semantic representation we select the predicate-argument structure that exists in most languages. In this structure a word is specified as a predicate and a number of word groups are considered as arguments accompanying the predicate. Those arguments are assigned different semantic categories depending on the roles that they play with respect to the predicate.</Paragraph>
    <Paragraph position="1"> We illustrate the predicate-argument structure in Figure 1 for the sentence &amp;quot;We are prepared to pursue aggressively completion of this transaction he says&amp;quot; taken from the PropBank corpus. The chosen predicate is the word pursue, and its arguments with their associated word groups are illustrated. Note that the word prepared is another predicate of the sentence possibly with different argument labels attached to the same or different word groups. For example, the word we is A1 of prepared. This process of selecting a predicate in a sentence, grouping sequences of words and assigning the semantic roles they play with respect to the chosen predicate is often referred to as semantic role labeling. We believe that a highly accurate extraction of this structure is vital for high performance in many NLP tasks such as information extraction, question answering,  sentence. Argument labels are in PropBank-style.</Paragraph>
    <Paragraph position="2"> Semantic role labeling based on predicate-argument structure was first explored in detail by (Gildea and Jurafsky, 2002). Since then several variants of the basic approach have been introduced using different features and different classifiers based on various machine learning techniques (Gildea and Palmer, 2002; Gildea and Hockenmaier, 2003; Surdeanu et. al., 2003; Chen and Rambow, 2003; Fleischman and Hovy, 2003; Hacioglu and Ward, 2003; Thompson et. al., 2003; Pradhan et. al., 2003b; Hacioglu, 2004). Large semantically annotated databases, like FrameNet (Baker et.al, 1998) and PropBank (Kingsbury and Palmer, 2002) have been used to train and test the classifiers. Most of those approaches can be divided into one of the following three broad classes with respect to the type of tokens classified; namely, constituent-by-constituent (C-by-C), phrase-by-phrase (P-by-P) and word-by-word (W-by-W) semantic role labelers.</Paragraph>
    <Paragraph position="3"> In C-by-C semantic role labeling, the syntactic tree representation of a sentence is linearized into a sequence of its syntactic constituents (nonterminals). Then each constituent is classified into one of several semantic roles using a number of features derived from the sentence structure or a linguistic context defined for the constituent token. In the P-by-P and W-by-W methods (Hacioglu, 2004; Hacioglu and Ward, 2003) the problem is formulated as a chunking task and the features are derived for each base phrase and word, respectively. The tokens were classified into one of the semantic labels using an IOB (inside-outside-begin) representation and a bank of SVM classifiers; a one-versus-all classifier has been used for each class.</Paragraph>
    <Paragraph position="5"> we completion of this transaction aggressively  predicate posted. The same tree with different semantic labels also exists in the corpus for predicate abated. In this paper, we introduce another approach that we refer to as the relation-by-relation (R-by-R) semantic role labeling. The method is based on dependency trees generated from constituency trees.</Paragraph>
    <Paragraph position="6"> Although the system currently does not use more information than C-by-C systems, the information is structured in a different manner and, consequently, the nature of some linguistic features is quite different. We point out that this information restructuring is very useful in localizing the semantic roles associated with the selected predicate, since the dependency trees directly encode the argument structure of lexical units populated at their nodes through dependency relations.</Paragraph>
    <Paragraph position="7"> A related work is reported in (Gildea and Hockenmaier, 2003). However, they use Combinatory Categorical Grammar (CCG) to derive the dependency relations. In addition, our method differs in the selection of dependency relations for labeling, in the creation of features and in the implementation of the classifier.</Paragraph>
    <Paragraph position="8"> Recently, there has been some interest in developing a deterministic machine-learning based approach for dependency parsing (Yamada and Matsumato, 2003). In addition to relatively easier portability to other domains and languages the deterministic dependency parsing promises algorithms that are robust and efficient. Therefore, an SRL algorithm based on dependency structures is expected to benefit from those properties.</Paragraph>
  </Section>
class="xml-element"></Paper>