<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3813">
  <Title>Matching Syntactic-Semantic Graphs for Semantic Relation Assignment</Title>
  <Section position="4" start_page="81" end_page="81" type="relat">
    <SectionTitle>
2 Related Work
</SectionTitle>
    <Paragraph position="0"> Some methods of semantic relation analysis rely on prede ned templates lled with information from processed texts (Baker et al., 1998). In other methods, lexical resources are speci cally tailored to meet the requirements of the domain (Rosario and Hearst, 2001) or the system (Gomez, 1998). Such systems extract information from some types of syntactic units (clauses in (Fillmore and Atkins, 1998; Gildea and Jurafsky, 2002; Hull and Gomez, 1996); noun phrases in (Hull and Gomez, 1996; Rosario et al., 2002)). Lists of semantic relations are designed to capture salient domain information.</Paragraph>
    <Paragraph position="1"> In the Rapid Knowledge Formation Project (RKF) a support system was developed for domain experts.</Paragraph>
    <Paragraph position="2"> It helps them build complex knowledge bases by combining components: events, entities and modiers (Clark and Porter, 1997). The system's interface facilitates the expert's task of creating and manipulating structures which represent domain concepts, and assigning them relations from a relation dictionary.</Paragraph>
    <Paragraph position="3"> In current work on semantic relation analysis, the focus is on semantic roles relations between verbs and their arguments. Most approaches rely on VerbNet (Kipper et al., 2000) and FrameNet (Baker et al., 1998) to provide associations between verbs and semantic roles, that are then mapped onto the current instance, as shown by the systems competing in semantic role labelling competitions (Carreras and Marquez, 2004; Carreras and Marquez, 2005) and also (Gildea and Jurafsky, 2002; Pradhan et al., 2005; Shi and Mihalcea, 2005).</Paragraph>
    <Paragraph position="4"> These systems share two ideas which make them different from the approach presented here: they all analyse verb-argument relations, and they all use machine learning or probabilistic approaches (Pradhan et al., 2005) to assign a label to a new instance. Labelling every instance relies on the same previously encoded knowledge (see (Carreras and Marquez, 2004; Carreras and Marquez, 2005) for an overview of the systems in the semantic role labelling competitions from 2004 and 2005). Pradhan et al. (2005) combine the outputs of multiple parsers to extract reliable syntactic information, which is translated into features for a machine learning experiment in assigning semantic roles.</Paragraph>
    <Paragraph position="5"> Our system analyses incrementally pairs of units coming from three syntactic levels clause (CL), intra-clause (or verb-argument, IC), noun-phrase (NP). There are no training and testing data sets. Instead of using previously built resources, the system relies on previously processed examples to nd the most appropriate relation for a current pair. Because the system does not rely on previously processed or annotated data, it is exible. It allows the user to customize the process for a speci c domain by choosing the syntactic units of interest and her own list of relations that best t the domain.</Paragraph>
    <Paragraph position="6"> It is also interesting to assess, using the current system con guration, the effect of syntactic information and incremental learning on semantic analysis. This is described in section 5.</Paragraph>
    <Paragraph position="7"> Because of these differences in the type of data used, and in the learning approach, the results we obtain cannot be compared to previous approaches.</Paragraph>
    <Paragraph position="8"> In order to show that the system does learn, we show that the number of examples for which it provides the correct answer increases with the number of examples previously analysed.</Paragraph>
  </Section>
class="xml-element"></Paper>