<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3813">
  <Title>Matching Syntactic-Semantic Graphs for Semantic Relation Assignment</Title>
  <Section position="3" start_page="0" end_page="81" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> When analysing texts, it is essential to see how elements of meaning are interconnected. This is an old idea. The rst chronicled endeavour to connect text elements and organise connections between them goes back to the 5th century B.C. and the work of Panini1. He was a grammarian who analysed Sanskrit (Misra, 1966). The idea resurfaced forcefully at several points in the more recent history of linguistic research (Tesni ere, 1959; Gruber, 1965; Fillmore, 1968). Now it has the attention of many researchers in natural language processing, as shown by recent research in semantic parsing and semantic  role labelling (Baker et al., 1998; Kipper et al., 2000; Carreras and Marquez, 2004; Carreras and Marquez, 2005; Atserias et al., 2001; Shi and Mihalcea, 2005).</Paragraph>
    <Paragraph position="1"> Graph-like structures are a natural way of organising one's impressions of a text seen from the perspective of connections between its simpler constituents of varying granularity, from sections through paragraphs, sentences, clauses, phrases, words to morphemes.</Paragraph>
    <Paragraph position="2"> In this work we pursue a well-known and often tacitly assumed line of thinking: connections at the syntactic level re ect connections at the semantic level (in other words, syntax carries meaning). Anecdotal support for this stance comes from the fact that the grammatical notion of case is the basis for semantic relations (Misra, 1966; Gruber, 1965; Fillmore, 1968). Tesni ere (1959), who proposes a grouping of verb arguments into actants and circumstances, gives a set of rules to connect speci c types of actants for example, agent or instrument to such grammatical elements as subject, direct object, indirect object. This idea was expanded to include nouns and their modi ers through verb nominalizations (Chomsky, 1970; Quirk et al., 1985).</Paragraph>
    <Paragraph position="3"> We work with sentences, clauses, phrases and words, using syntactic structures generated by a parser. Our system incrementally processes a text, and extracts pairs of text units: two clauses, a verb and each of its arguments, a noun and each of its modi ers. For each pair of units, the system builds a syntactic graph surrounding the main element (main clause, head verb, head noun). It then tries to nd among the previously processed instances another main element with a matching syntactic graph. If such a graph is found, then the system maps previously assigned semantic relations onto the current syntactic graph. We have a list of 47 relations that manifest themselves in compound clauses, inside a simple clause or in noun phrases. The list, a synthesis of a number of relation lists cited in the literature, has been designed to be general, domain-independent (Barker et al., 1997a).</Paragraph>
    <Paragraph position="4"> Section 2 overviews research in semantic relation analysis. Section 3 describes the text we used in ex- null periments, and the semantic relation list. Section 4 looks in detail at the graph-matching heuristic. Section 5 describes the experimental setting and shows how often the heuristic was used when processing the input text. We show in detail our ndings about syntactic levels (how often graph matching helped assign a relation between two clauses, a verb and its arguments, or a noun and its modi er) and about the accuracy of the suggestion. Discussion and conclusions appear in Section 6.</Paragraph>
  </Section>
class="xml-element"></Paper>