<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2105">
  <Title>Semantic Interpretation of Prepositions for NLP Applications</Title>
  <Section position="2" start_page="0" end_page="29" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Advanced NLP applications such as question answering require deep semantic interpretation. In this context, prepositions play an important role since they encode relational information. The proper semantic analysis of prepositional phrases is faced with various problems: (1) There is the well-known problem of attachment ambiguities.</Paragraph>
    <Paragraph position="1"> (2) Prepositions are highly polysemous, i.e. their interpretation is typically context dependent. (3) Prepositions often occur in collocations, where their interpretation is irregular.</Paragraph>
    <Paragraph position="2"> Although a large amount of work in the NLP community has focused on resolving attachment ambiguities, there are only first steps towards a systematic description of preposition semantics which has sufficient coverage for NLP applications (Litkowski and Hargraves, 2005; Saint-Dizier, 2005). The automatic interpretation of prepositions in English has been tackled, for example, by Litkowski (2002), who presents hand-crafted disambiguation rules, and O'Hara and Wiebe (2003), who propose a statistical approach based on collocations. However, in order to be applicable for semantic inference, the representation of preposition semantics should ideally be integrated within a full-fledged knowledge representation formalism.</Paragraph>
    <Paragraph position="3"> In spite of the broad linguistic investigations on preposition semantics,1 the corresponding results have seldom found their way into real NLP applications. Information retrieval systems, on the other hand, which claim to use NLP techniques often do not cope with the semantic content of prepositions at all (even if they bear the term semantic in their title, as with Latent Semantic Analysis (Letsche and Berry, 1997)). In many cases prepositions are even dropped as stop words in such systems. If one really wants to syntactico-semantically analyze texts and derive formal semantic representations, the interpretation of prepositions and especially the disambiguation of their different readings is a central problem in Indoeuropean languages like English, French, Russian, and German.</Paragraph>
    <Paragraph position="4"> In this paper we describe the semantic treatmentofthisproblemforGerman,usingtheknowl- null edge representation formalism of Multilayered Extended Semantic Networks (MultiNet) (Helbig, 2006). The advantage of this approach is its applicability to different languages and different processes of automatic natural language understanding. Since MultiNet complies with the criteria of universality, homogeneity, and interoperability (Helbig, 2006, Chapter 1), it can be used to for- null regular She lives in Berlin.</Paragraph>
    <Paragraph position="5"> They met in August. null irregular He believes in destiny.</Paragraph>
    <Paragraph position="6"> He was killed on the run.</Paragraph>
    <Paragraph position="7"> 2003) as well as that of sentences and texts (see (Leveling and Hartrumpf, 2005), where MultiNet has been employed for semantic annotation of large corpora). It can also be used as a semantic interlingua throughout all NLP modules and all applications of an NLP system (Leveling, 2005).</Paragraph>
    <Paragraph position="8"> Typical applications that can profit from a precise PP interpretation component are question answering (QA) systems and natural language interfaces.</Paragraph>
  </Section>
class="xml-element"></Paper>